Spaces:
Running
Running
| {"title": "Polish linguistic and cultural competency benchmark", "paper": "https://arxiv.org/abs/2503.00995", "citation": "@misc{dadas2025evaluatingpolishlinguisticcultural,\n title={Evaluating Polish linguistic and cultural competency in large language models}, \n author={Sławomir Dadas and Małgorzata Grębowiec and Michał Perełkiewicz and Rafał Poświata},\n year={2025},\n eprint={2503.00995},\n archivePrefix={arXiv},\n primaryClass={cs.CL},\n url={https://arxiv.org/abs/2503.00995}, \n}", "options": {"closeable": false, "expandable": false, "showHelp": false, "showFooter": false, "average": false, "tasksWon": false}, "metrics": [{"id": "Accuracy", "description": "Accuracy", "greaterIsBetter": true}], "taskGroups": [{"id": "__global__", "name": " ", "expanded": true}], "tasks": [{"id": "art & entertainment", "name": "art &\nentertainment", "precision": 0}, {"id": "culture & tradition", "name": "culture &\ntradition", "precision": 0}, {"id": "geography", "name": "geography", "precision": 0}, {"id": "grammar", "name": "grammar", "precision": 0}, {"id": "history", "name": "history", "precision": 0}, {"id": "vocab", "name": "vocab", "precision": 0}], "models": [{"id": "bielik-0.1", "name": "Bielik-0.1", "url": "https://huggingface.co/speakleash/Bielik-7B-Instruct-v0.1", "columns": {"Provider": "SpeakLeash"}, "params": "7.2B"}, {"id": "bielik-2.1", "name": "Bielik-2.1", "url": "https://huggingface.co/speakleash/Bielik-11B-v2.1-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "11.2B"}, {"id": "bielik-2.2", "name": "Bielik-2.2", "url": "https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "11.2B"}, {"id": "bielik-2.3", "name": "Bielik-2.3", "url": "https://huggingface.co/speakleash/Bielik-11B-v2.3-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "11.2B"}, {"id": "bielik-2.5", "name": "Bielik-2.5", "url": "https://huggingface.co/speakleash/Bielik-11B-v2.6-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "11.2B"}, {"id": "bielik-2.6", "name": "Bielik-2.6", "url": "https://huggingface.co/speakleash/Bielik-11B-v2.6-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "11.2B"}, {"id": "bielik-3-4.5b", "name": "Bielik-4.5B-v3.0-Instruct", "url": "https://huggingface.co/speakleash/Bielik-4.5B-v3.0-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "4.8B"}, {"id": "bielik-3-1.5b", "name": "Bielik-1.5B-v3.0-Instruct", "url": "https://huggingface.co/speakleash/Bielik-1.5B-v3.0-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "1.6B"}, {"id": "Bielik-11B-v3.0-Instruct", "name": "Bielik-11B-v3.0-Instruct", "url": "https://huggingface.co/speakleash/Bielik-11B-v3.0-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "11.2B"}, {"id": "Bielik-Minitron-7B-v3.0-Instruct", "name": "Bielik-Minitron-7B-v3.0-Instruct", "url": "https://huggingface.co/speakleash/Bielik-Minitron-7B-v3.0-Instruct", "columns": {"Provider": "SpeakLeash"}, "params": "7.5B"}, {"id": "llama-3.1-8b", "name": "Llama-3.1-8B", "url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "columns": {"Provider": "Meta"}, "params": "8.0B"}, {"id": "llama-3.1-70b", "name": "Llama-3.1-70B", "url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "columns": {"Provider": "Meta"}, "params": "70.6B"}, {"id": "llama-3.0-70b", "name": "Llama-3.0-70B", "url": "https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct", "columns": {"Provider": "Meta"}, "params": "70.6B"}, {"id": "llama-3.3-70b", "name": "Llama-3.3-70B", "url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "columns": {"Provider": "Meta"}, "params": "70.6B"}, {"id": "llama-3.1-405b", "name": "Llama-3.1-405b", "url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "columns": {"Provider": "Meta"}, "params": "405.9B"}, {"id": "claude-3-5-haiku-20241022", "name": "Claude-3.5-Haiku-20241022", "columns": {"Provider": "Anthropic"}}, {"id": "claude-3-opus", "name": "Claude-3-Opus", "columns": {"Provider": "Anthropic"}}, {"id": "claude-3.5-sonnet", "name": "Claude-3.5-Sonnet-20241022", "columns": {"Provider": "Anthropic"}}, {"id": "claude-3.5-sonnet-20240620", "name": "Claude-3.5-Sonnet-20240620", "columns": {"Provider": "Anthropic"}}, {"id": "claude-3.7-sonnet", "name": "Claude-3.7-Sonnet", "columns": {"Provider": "Anthropic"}}, {"id": "claude-3.7-sonnet-thinking", "name": "Claude-3.7-Sonnet-Thinking", "columns": {"Provider": "Anthropic"}}, {"id": "claude-3-sonnet", "name": "Claude-3.0-Sonnet", "columns": {"Provider": "Anthropic"}}, {"id": "claude-4-sonnet", "name": "Claude-Sonnet-4", "columns": {"Provider": "Anthropic"}}, {"id": "claude-4-opus", "name": "Claude-Opus-4", "columns": {"Provider": "Anthropic"}}, {"id": "claude-opus-4.1", "name": "Claude-Opus-4.1", "columns": {"Provider": "Anthropic"}}, {"id": "claude-opus-4.5", "name": "Claude-Opus-4.5", "columns": {"Provider": "Anthropic"}}, {"id": "claude-opus-4.6", "name": "Claude-Opus-4.6", "columns": {"Provider": "Anthropic"}}, {"id": "claude-opus-4.7", "name": "Claude-Opus-4.7", "columns": {"Provider": "Anthropic"}}, {"id": "claude-sonnet-4.5", "name": "Claude-Sonnet-4.5", "columns": {"Provider": "Anthropic"}}, {"id": "claude-sonnet-4.6", "name": "Claude-Sonnet-4.6", "columns": {"Provider": "Anthropic"}}, {"id": "claude-haiku-4.5", "name": "Claude-Haiku-4.5", "columns": {"Provider": "Anthropic"}}, {"id": "ministral-3b-2512", "name": "Ministral-3b-2512", "url": "https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512", "columns": {"Provider": "Mistral"}, "params": "3B"}, {"id": "ministral-8b-2512", "name": "Ministral-8b-2512", "url": "https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512", "columns": {"Provider": "Mistral"}, "params": "8.9B"}, {"id": "ministral-14b-2512", "name": "Ministral-14b-2512", "url": "https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512", "columns": {"Provider": "Mistral"}, "params": "14B"}, {"id": "ministral-8b", "name": "Ministral-8b", "url": "https://huggingface.co/mistralai/Ministral-8B-Instruct-2410", "columns": {"Provider": "Mistral"}, "params": "8B"}, {"id": "mistral-7b-v0.3", "name": "Mistral-7b-v0.3", "url": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3", "columns": {"Provider": "Mistral"}, "params": "7.2B"}, {"id": "mistral-large-2407", "name": "Mistral-Large-2407", "url": "https://huggingface.co/mistralai/Mistral-Large-Instruct-2407", "columns": {"Provider": "Mistral"}, "params": "123B"}, {"id": "mistral-large-2411", "name": "Mistral-Large-2411", "url": "https://huggingface.co/mistralai/Mistral-Large-Instruct-2411", "columns": {"Provider": "Mistral"}, "params": "123B"}, {"id": "mistral-large-2512", "name": "Mistral-Large-2512", "url": "https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512", "columns": {"Provider": "Mistral"}, "params": "675B"}, {"id": "mistral-nemo", "name": "Mistral-Nemo", "url": "https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407", "columns": {"Provider": "Mistral"}, "params": "12.2B"}, {"id": "mixtral-8x22b-instruct", "name": "Mixtral-8x22b", "url": "https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1", "columns": {"Provider": "Mistral"}, "params": "140.6B"}, {"id": "mixtral-8x7b-instruct", "name": "Mixtral-8x7b", "url": "https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1", "columns": {"Provider": "Mistral"}, "params": "46.7B"}, {"id": "Mistral-Small-24B-Instruct-2501", "name": "Mistral-Small-24B-2501", "url": "https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501", "columns": {"Provider": "Mistral"}, "params": "24B"}, {"id": "mistral-small-3.1-24b-2503", "name": "Mistral-Small-3.1-24B-2503", "url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "columns": {"Provider": "Mistral"}, "params": "24B"}, {"id": "mistral-small-3.2-24b-2506", "name": "Mistral-Small-3.2-24B-2506", "url": "https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "columns": {"Provider": "Mistral"}, "params": "24B"}, {"id": "mistral-medium-3", "name": "Mistral-Medium-3", "columns": {"Provider": "Mistral"}}, {"id": "Mistral-Medium-3.5", "name": "Mistral-Medium-3.5", "url": "https://huggingface.co/mistralai/Mistral-Medium-3.5-128B", "columns": {"Provider": "Mistral"}, "params": "127.7B"}, {"id": "Mistral-Small-4", "name": "Mistral-Small-4", "url": "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603", "columns": {"Provider": "Mistral"}, "params": "119.4B"}, {"id": "magistral-small-2506", "name": "Magistral-Small-2506", "url": "https://huggingface.co/mistralai/Magistral-Small-2506", "columns": {"Provider": "Mistral"}, "params": "23.6B"}, {"id": "wizardlm-2-8x22b", "name": "WizardLM-2-8x22b", "url": "https://huggingface.co/alpindale/WizardLM-2-8x22B", "columns": {"Provider": "Microsoft"}, "params": "140.6B"}, {"id": "gpt-3.5-turbo", "name": "GPT-3.5-turbo", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4-turbo", "name": "GPT-4-turbo", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4o-2024-05-13", "name": "GPT-4o-2024-05-13", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4o-2024-08-06", "name": "GPT-4o-2024-08-06", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4o-2024-11-20", "name": "GPT-4o-2024-11-20", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4o-mini-2024-07-18", "name": "GPT-4o-mini-2024-07-18", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4", "name": "GPT-4", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4.5-preview-2025-02-27", "name": "GPT-4.5-preview-2025-02-27", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4.1-2025-04-14", "name": "GPT-4.1-2025-04-14", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4.1-mini-2025-04-14", "name": "GPT-4.1-mini-2025-04-14", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-4.1-nano-2025-04-14", "name": "GPT-4.1-nano-2025-04-14", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.5-no", "name": "GPT-5.5 (no reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.5-low", "name": "GPT-5.5 (low reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.5-high", "name": "GPT-5.5 (high reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5-2025-08-07", "name": "GPT-5-2025-08-07", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5-mini-2025-08-07", "name": "GPT-5-mini-2025-08-07", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5-nano-2025-08-07", "name": "GPT-5-nano-2025-08-07", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5-pro-2025-10-06", "name": "GPT-5-Pro-2025-10-06 (high reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.1-2025-11-13", "name": "GPT-5.1-2025-11-13 (default reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.1-2025-11-13-high", "name": "GPT-5.1-2025-11-13 (high reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.2-2025-12-11", "name": "GPT-5.2-2025-12-11 (medium reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.2-2025-12-11-high", "name": "GPT-5.2-2025-12-11 (high reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.2-2025-12-11-xhigh", "name": "GPT-5.2-2025-12-11 (xhigh reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.2-2025-12-11-no", "name": "GPT-5.2-2025-12-11 (no reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.4-2026-03-05-high", "name": "GPT-5.4-2026-03-05 (high reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.4-2026-03-05-low", "name": "GPT-5.4-2026-03-05 (low reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.4-2026-03-05-no", "name": "GPT-5.4-2026-03-05 (no reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.4-mini-2026-03-17-high", "name": "GPT-5.4-mini-2026-03-17 (high reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.4-mini-2026-03-17-no", "name": "GPT-5.4-mini-2026-03-17 (no reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.4-nano-2026-03-17-high", "name": "GPT-5.4-nano-2026-03-17 (high reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gpt-5.4-nano-2026-03-17-no", "name": "GPT-5.4-nano-2026-03-17 (no reasoning)", "columns": {"Provider": "OpenAI"}}, {"id": "gemma-2-27b", "name": "Gemma-2-27b", "url": "https://huggingface.co/google/gemma-2-27b-it", "columns": {"Provider": "Google"}, "params": "27.2B"}, {"id": "gemma-2-9b", "name": "Gemma-2-9b", "url": "https://huggingface.co/google/gemma-2-9b-it", "columns": {"Provider": "Google"}, "params": "9.2B"}, {"id": "gemma-3-27b", "name": "Gemma-3-27b", "url": "https://huggingface.co/google/gemma-3-27b-it", "columns": {"Provider": "Google"}, "params": "27.4B"}, {"id": "gemma-4-E2B-it", "name": "Gemma-4-E2B-it (reasoning disabled)", "url": "https://huggingface.co/google/gemma-4-E2B-it", "columns": {"Provider": "Google"}, "params": "5.1B"}, {"id": "gemma-4-E4B-it", "name": "Gemma-4-E4B-it (reasoning disabled)", "url": "https://huggingface.co/google/gemma-4-E4B-it", "columns": {"Provider": "Google"}, "params": "8.0B"}, {"id": "gemma-4-26B-A4B-it", "name": "Gemma-4-26B-A4B-it (reasoning disabled)", "url": "https://huggingface.co/google/gemma-4-26B-A4B-it", "columns": {"Provider": "Google"}, "params": "26.5B"}, {"id": "gemma-4-31B-it", "name": "Gemma-4-31B-it (reasoning disabled)", "url": "https://huggingface.co/google/gemma-4-31B-it", "columns": {"Provider": "Google"}, "params": "32.7B"}, {"id": "gemma-4-E2B-it-reasoning", "name": "Gemma-4-E2B-it (reasoning enabled)", "url": "https://huggingface.co/google/gemma-4-E2B-it", "columns": {"Provider": "Google"}, "params": "5.1B"}, {"id": "gemma-4-E4B-it-reasoning", "name": "Gemma-4-E4B-it (reasoning enabled)", "url": "https://huggingface.co/google/gemma-4-E4B-it", "columns": {"Provider": "Google"}, "params": "8.0B"}, {"id": "gemma-4-26B-A4B-it-reasoning", "name": "Gemma-4-26B-A4B-it (reasoning enabled)", "url": "https://huggingface.co/google/gemma-4-26B-A4B-it", "columns": {"Provider": "Google"}, "params": "26.5B"}, {"id": "gemma-4-31B-it-reasoning", "name": "Gemma-4-31B-it (reasoning enabled)", "url": "https://huggingface.co/google/gemma-4-31B-it", "columns": {"Provider": "Google"}, "params": "32.7B"}, {"id": "qwen-2.5-72b", "name": "Qwen-2.5-72b", "url": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct", "columns": {"Provider": "Alibaba"}, "params": "72.7B"}, {"id": "qwen-2.5-7b", "name": "Qwen-2.5-7b", "url": "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct", "columns": {"Provider": "Alibaba"}, "params": "7.6B"}, {"id": "qwen-2.5-14B", "name": "Qwen-2.5-14b", "url": "https://huggingface.co/Qwen/Qwen2.5-14B-Instruct", "columns": {"Provider": "Alibaba"}, "params": "14.8B"}, {"id": "qwen-2.5-32B", "name": "Qwen-2.5-32b", "url": "https://huggingface.co/Qwen/Qwen2.5-32B-Instruct", "columns": {"Provider": "Alibaba"}, "params": "32.8B"}, {"id": "qwen-turbo-2024-11-01", "name": "Qwen-Turbo-2024-11-01", "columns": {"Provider": "Alibaba"}}, {"id": "qwen3.6-plus", "name": "Qwen3.6-Plus", "columns": {"Provider": "Alibaba"}}, {"id": "qwen-plus", "name": "Qwen-Plus", "columns": {"Provider": "Alibaba"}}, {"id": "qwen-max", "name": "Qwen-Max", "columns": {"Provider": "Alibaba"}}, {"id": "qwen3-max", "name": "Qwen3-Max", "columns": {"Provider": "Alibaba"}}, {"id": "qwen3.7-max", "name": "Qwen3.7-Max", "columns": {"Provider": "Alibaba"}}, {"id": "qwen3-235b-a22b", "name": "Qwen3-235B-A22B", "url": "https://huggingface.co/Qwen/Qwen3-235B-A22B", "columns": {"Provider": "Alibaba"}, "params": "235.1B"}, {"id": "qwen3-30b-a3b", "name": "Qwen3-30B-A3B", "url": "https://huggingface.co/Qwen/Qwen3-30B-A3B", "columns": {"Provider": "Alibaba"}, "params": "30.5B"}, {"id": "qwen3-32b", "name": "Qwen3-32B", "url": "https://huggingface.co/Qwen/Qwen3-32B", "columns": {"Provider": "Alibaba"}, "params": "32.8B"}, {"id": "qwen3-14b", "name": "Qwen3-14B", "url": "https://huggingface.co/Qwen/Qwen3-14B", "columns": {"Provider": "Alibaba"}, "params": "14.8B"}, {"id": "qwen3-8b", "name": "Qwen3-8B", "url": "https://huggingface.co/Qwen/Qwen3-8B", "columns": {"Provider": "Alibaba"}, "params": "8.2B"}, {"id": "qwen3-next-80b-a3b-instruct", "name": "Qwen3-Next-80B-A3B-Instruct", "url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "columns": {"Provider": "Alibaba"}, "params": "81.3B"}, {"id": "qwen3-next-80b-a3b-thinking", "name": "Qwen3-Next-80B-A3B-Thinking", "url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking", "columns": {"Provider": "Alibaba"}, "params": "80B"}, {"id": "command-r-plus-04-2024", "name": "Command-R-Plus-04-2024", "url": "https://huggingface.co/CohereForAI/c4ai-command-r-plus", "columns": {"Provider": "Cohere"}, "params": "104B"}, {"id": "command-r-plus-08-2024", "name": "Command-R-Plus-08-2024", "url": "https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024", "columns": {"Provider": "Cohere"}, "params": "103.8B"}, {"id": "command-r7b", "name": "Command-R7B", "url": "https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024", "columns": {"Provider": "Cohere"}, "params": "103.8B"}, {"id": "command-a-03-2025", "name": "Command-A-03-2025", "url": "https://huggingface.co/CohereForAI/c4ai-command-a-03-2025", "columns": {"Provider": "Cohere"}, "params": "111.1B"}, {"id": "grok-2-1212", "name": "Grok-2-1212", "columns": {"Provider": "xAI"}}, {"id": "gemini-2.0-flash-experimental", "name": "Gemini-2.0-Flash-Experimental", "columns": {"Provider": "Google"}}, {"id": "gemini-2.0-flash-thinking-exp-01-21", "name": "Gemini-2.0-Flash-Thinking-Exp-01-21", "columns": {"Provider": "Google"}}, {"id": "gemini-2.5-pro-exp-03-25", "name": "Gemini-2.5-Pro-Exp-03-25", "columns": {"Provider": "Google"}}, {"id": "gemini-2.5-flash-preview-04-17", "name": "Gemini-2.5-Flash-Preview-04-17", "columns": {"Provider": "Google"}}, {"id": "gemini-2.5-pro-preview-06-05", "name": "Gemini-2.5-Pro-Preview-06-05", "columns": {"Provider": "Google"}}, {"id": "gemini-3.0-pro-preview", "name": "Gemini-3.0-Pro-Preview", "columns": {"Provider": "Google"}}, {"id": "gemini-3.1-pro-preview", "name": "Gemini-3.1-Pro-Preview", "columns": {"Provider": "Google"}}, {"id": "gemini-3-flash-preview", "name": "Gemini-3-Flash-Preview", "columns": {"Provider": "Google"}}, {"id": "gemini-3.5-flash", "name": "Gemini-3.5-Flash", "columns": {"Provider": "Google"}}, {"id": "o1-mini-2024-09-12", "name": "O1-mini-2024-09-12", "columns": {"Provider": "OpenAI"}}, {"id": "o1-2024-12-17", "name": "O1-2024-12-17", "columns": {"Provider": "OpenAI"}}, {"id": "o3-mini-2025-01-31", "name": "O3-mini-2025-01-31", "columns": {"Provider": "OpenAI"}}, {"id": "o4-mini-2025-04-16", "name": "O4-Mini-2025-04-16", "columns": {"Provider": "OpenAI"}}, {"id": "o3-2025-04-16", "name": "O3-2025-04-16", "columns": {"Provider": "OpenAI"}}, {"id": "gemini-exp-1206", "name": "Gemini-Exp-1206", "columns": {"Provider": "Google"}}, {"id": "deepseek-v4-flash", "name": "DeepSeek-V4-Flash", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash", "columns": {"Provider": "DeepSeek"}, "params": "158.1B"}, {"id": "deepseek-v4-pro", "name": "DeepSeek-V4-Pro", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro", "columns": {"Provider": "DeepSeek"}, "params": "861.6B"}, {"id": "deepseek-v3", "name": "DeepSeek-v3", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "columns": {"Provider": "DeepSeek"}, "params": "684.5B"}, {"id": "deepseek-v3-0324", "name": "DeepSeek-v3-0324", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324", "columns": {"Provider": "DeepSeek"}, "params": "684.5B"}, {"id": "deepseek-v3.1", "name": "DeepSeek-v3.1 (no thinking)", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "columns": {"Provider": "DeepSeek"}, "params": "684.5B"}, {"id": "deepseek-v3.1-thinking", "name": "DeepSeek-v3.1 (thinking)", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "columns": {"Provider": "DeepSeek"}, "params": "684.5B"}, {"id": "deepseek-v3.2-exp", "name": "DeepSeek-v3.2-Exp", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "columns": {"Provider": "DeepSeek"}, "params": "685.4B"}, {"id": "deepseek-v3.2", "name": "DeepSeek-V3.2", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "columns": {"Provider": "DeepSeek"}, "params": "685.4B"}, {"id": "deepseek-v3.2-speciale", "name": "DeepSeek-V3.2-Speciale", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale", "columns": {"Provider": "DeepSeek"}, "params": "685B"}, {"id": "deepseek-r1", "name": "DeepSeek-R1", "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "columns": {"Provider": "DeepSeek"}, "params": "684.5B"}, {"id": "deepseek-r1-0528", "name": "DeepSeek-R1-0528", "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "columns": {"Provider": "DeepSeek"}, "params": "684.5B"}, {"id": "gemini-pro-1.5", "name": "Gemini-Pro-1.5", "columns": {"Provider": "Google"}}, {"id": "gemini-flash-1.5", "name": "Gemini-Flash-1.5", "columns": {"Provider": "Google"}}, {"id": "phi-4", "name": "Phi-4", "url": "https://huggingface.co/microsoft/phi-4", "columns": {"Provider": "Microsoft"}, "params": "14B"}, {"id": "PLLuM-12B-nc-chat", "name": "PLLuM-12B-nc-chat", "url": "https://huggingface.co/CYFRAGOVPL/PLLuM-12B-nc-chat", "columns": {"Provider": "PLLuM"}, "params": "12.2B"}, {"id": "pllum-12b-nc-chat-250715", "name": "PLLuM-12B-nc-chat-250715", "url": "https://huggingface.co/CYFRAGOVPL/pllum-12b-nc-chat-250715", "columns": {"Provider": "PLLuM"}, "params": "12.2B"}, {"id": "PLLuM-8x7B-nc-chat", "name": "PLLuM-8x7B-nc-chat", "url": "https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-nc-chat", "columns": {"Provider": "PLLuM"}, "params": "46.7B"}, {"id": "llama-3.1-tulu-3-405b", "name": "Llama-3.1-Tulu-3-405B", "url": "https://huggingface.co/allenai/Llama-3.1-Tulu-3-405B", "columns": {"Provider": "Meta"}, "params": "405B"}, {"id": "Llama-PLLuM-8B-chat", "name": "Llama-PLLuM-8B-chat", "url": "https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-chat", "columns": {"Provider": "PLLuM"}, "params": "8.0B"}, {"id": "PLLuM-12B-chat", "name": "PLLuM-12B-chat", "url": "https://huggingface.co/CYFRAGOVPL/PLLuM-12B-chat", "columns": {"Provider": "PLLuM"}, "params": "12.2B"}, {"id": "Llama-PLLuM-70B-chat", "name": "Llama-PLLuM-70B-chat", "url": "https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-chat", "columns": {"Provider": "PLLuM"}, "params": "70.6B"}, {"id": "Llama-PLLuM-70B-chat-250801", "name": "Llama-PLLuM-70B-chat-250801", "url": "https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-chat-250801", "columns": {"Provider": "PLLuM"}, "params": "70.6B"}, {"id": "PLLuM-8x7B-chat", "name": "PLLuM-8x7B-chat", "url": "https://huggingface.co/CYFRAGOVPL/PLLuM-8x7B-chat", "columns": {"Provider": "PLLuM"}, "params": "46.7B"}, {"id": "Llama-PLLuM-8B-chat-2512", "name": "Llama-PLLuM-8B-chat-2512", "url": "https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-chat-2512", "columns": {"Provider": "PLLuM"}, "params": "8B"}, {"id": "PLLuM-4B-chat-2512", "name": "PLLuM-4B-chat-2512", "url": "https://huggingface.co/CYFRAGOVPL/PLLuM-4B-chat-2512", "columns": {"Provider": "PLLuM"}, "params": "4.3B"}, {"id": "PLLuM-12B-chat-2512", "name": "PLLuM-12B-chat-2512", "url": "https://huggingface.co/CYFRAGOVPL/PLLuM-12B-chat-2512", "columns": {"Provider": "PLLuM"}, "params": "12B"}, {"id": "Llama-PLLuM-70B-chat-2512", "name": "Llama-PLLuM-70B-chat-2512", "url": "https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-70B-chat-2512", "columns": {"Provider": "PLLuM"}, "params": "70.6B"}, {"id": "EuroLLM-9B", "name": "EuroLLM-9B", "url": "https://huggingface.co/utter-project/EuroLLM-9B-Instruct", "columns": {"Provider": "UTTER"}, "params": "9B"}, {"id": "llama-4-maverick", "name": "Llama-4-Maverick", "url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct", "columns": {"Provider": "Meta"}, "params": "401.6B"}, {"id": "llama-4-scout", "name": "Llama-4-Scout", "url": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct", "columns": {"Provider": "Meta"}, "params": "109B"}, {"id": "grok-3", "name": "Grok-3-Beta", "columns": {"Provider": "xAI"}}, {"id": "grok-3-mini", "name": "Grok-3-Mini-Beta", "columns": {"Provider": "xAI"}}, {"id": "grok-4", "name": "Grok-4", "columns": {"Provider": "xAI"}}, {"id": "grok-4-fast", "name": "Grok-4-Fast", "columns": {"Provider": "xAI"}}, {"id": "grok-4.1-fast", "name": "Grok-4.1-Fast", "columns": {"Provider": "xAI"}}, {"id": "grok-4.20", "name": "Grok-4.20", "columns": {"Provider": "xAI"}}, {"id": "grok-4.3", "name": "Grok-4.3", "columns": {"Provider": "xAI"}}, {"id": "kimi-k2", "name": "Kimi-K2", "url": "https://huggingface.co/moonshotai/Kimi-K2-Instruct", "columns": {"Provider": "Moonshot.AI"}, "params": "1.0T"}, {"id": "kimi-k2-0905", "name": "Kimi-K2-0905", "url": "https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905", "columns": {"Provider": "Moonshot.AI"}, "params": "1.0T"}, {"id": "kimi-k2-thinking", "name": "Kimi-K2-Thinking", "url": "https://huggingface.co/moonshotai/Kimi-K2-Thinking", "columns": {"Provider": "Moonshot.AI"}, "params": "1.1T"}, {"id": "kimi-k2.5", "name": "Kimi-K2.5", "url": "https://huggingface.co/moonshotai/Kimi-K2.5", "columns": {"Provider": "Moonshot.AI"}, "params": "1.1T"}, {"id": "kimi-k2.6", "name": "Kimi-K2.6", "url": "https://huggingface.co/moonshotai/Kimi-K2.6", "columns": {"Provider": "Moonshot.AI"}, "params": "1.1T"}, {"id": "glm-4.5", "name": "GLM-4.5", "url": "https://huggingface.co/zai-org/GLM-4.5", "columns": {"Provider": "Zhipu AI"}, "params": "358.3B"}, {"id": "glm-4.6", "name": "GLM-4.6", "url": "https://huggingface.co/zai-org/GLM-4.6", "columns": {"Provider": "Zhipu AI"}, "params": "356.8B"}, {"id": "glm-4.7", "name": "GLM-4.7", "url": "https://huggingface.co/zai-org/GLM-4.7", "columns": {"Provider": "Zhipu AI"}, "params": "358.3B"}, {"id": "glm-5", "name": "GLM-5", "url": "https://huggingface.co/zai-org/GLM-5", "columns": {"Provider": "Zhipu AI"}, "params": "753.9B"}, {"id": "glm-5.1", "name": "GLM-5.1", "url": "https://huggingface.co/zai-org/GLM-5.1", "columns": {"Provider": "Zhipu AI"}, "params": "753.9B"}, {"id": "glm-4.7-flash", "name": "GLM-4.7-Flash", "url": "https://huggingface.co/zai-org/GLM-4.7-Flash", "columns": {"Provider": "Zhipu AI"}, "params": "31.2B"}, {"id": "glm-4.5-air", "name": "GLM-4.5-Air", "url": "https://huggingface.co/zai-org/GLM-4.5-Air", "columns": {"Provider": "Zhipu AI"}, "params": "110.5B"}, {"id": "gpt-oss-120b", "name": "GPT-OSS-120b", "url": "https://huggingface.co/openai/gpt-oss-120b", "columns": {"Provider": "OpenAI"}, "params": "120.4B"}, {"id": "gpt-oss-20b", "name": "GPT-OSS-20b", "url": "https://huggingface.co/openai/gpt-oss-20b", "columns": {"Provider": "OpenAI"}, "params": "21.5B"}, {"id": "minimax-m2.5", "name": "MiniMax-M2.5", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.5", "columns": {"Provider": "MiniMaxAI"}, "params": "228.7B"}, {"id": "minimax-m2.7", "name": "MiniMax-M2.7", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.7", "columns": {"Provider": "MiniMaxAI"}, "params": "228.7B"}, {"id": "qwen3.5-397b-a17b", "name": "Qwen3.5-397B-A17B", "url": "https://huggingface.co/Qwen/Qwen3.5-397B-A17B", "columns": {"Provider": "Alibaba"}, "params": "403.4B"}, {"id": "Qwen3.5-27B", "name": "Qwen3.5-27B", "url": "https://huggingface.co/Qwen/Qwen3.5-27B", "columns": {"Provider": "Alibaba"}, "params": "27.8B"}, {"id": "Qwen3.6-27B", "name": "Qwen3.6-27B", "url": "https://huggingface.co/Qwen/Qwen3.6-27B", "columns": {"Provider": "Alibaba"}, "params": "27.8B"}, {"id": "Qwen3.5-35B-A3B", "name": "Qwen3.5-35B-A3B", "url": "https://huggingface.co/Qwen/Qwen3.5-35B-A3B", "columns": {"Provider": "Alibaba"}, "params": "36.0B"}, {"id": "Qwen3.6-35B-A3B", "name": "Qwen3.6-35B-A3B", "url": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "columns": {"Provider": "Alibaba"}, "params": "36.0B"}, {"id": "Qwen3.5-122B-A10B", "name": "Qwen3.5-122B-A10B", "url": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B", "columns": {"Provider": "Alibaba"}, "params": "125.1B"}, {"id": "Qwen3.5-9B", "name": "Qwen3.5-9B", "url": "https://huggingface.co/Qwen/Qwen3.5-9B", "columns": {"Provider": "Alibaba"}, "params": "9.7B"}, {"id": "Qwen3.5-4B", "name": "Qwen3.5-4B", "url": "https://huggingface.co/Qwen/Qwen3.5-4B", "columns": {"Provider": "Alibaba"}, "params": "4.7B"}, {"id": "Qwen3.5-2B", "name": "Qwen3.5-2B", "url": "https://huggingface.co/Qwen/Qwen3.5-2B", "columns": {"Provider": "Alibaba"}, "params": "2.3B"}, {"id": "mimo-v2-pro", "name": "MiMo-V2-Pro", "columns": {"Provider": "Xiaomi"}}], "results": [{"id": "bielik-0.1", "tags": [], "timestamp": "22/12/2024,10:43:42", "results": {"art & entertainment": {"Accuracy": 43.0}, "culture & tradition": {"Accuracy": 52.0}, "geography": {"Accuracy": 61.0}, "grammar": {"Accuracy": 29.0}, "history": {"Accuracy": 58.0}, "vocab": {"Accuracy": 37.0}}, "columns": {}}, {"id": "bielik-2.1", "tags": [], "timestamp": "22/12/2024,10:47:13", "results": {"art & entertainment": {"Accuracy": 55.0}, "culture & tradition": {"Accuracy": 64.0}, "geography": {"Accuracy": 68.0}, "grammar": {"Accuracy": 50.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 56.0}}, "columns": {}}, {"id": "bielik-2.2", "tags": [], "timestamp": "22/12/2024,10:50:47", "results": {"art & entertainment": {"Accuracy": 54.0}, "culture & tradition": {"Accuracy": 60.0}, "geography": {"Accuracy": 72.0}, "grammar": {"Accuracy": 53.0}, "history": {"Accuracy": 77.0}, "vocab": {"Accuracy": 62.0}}, "columns": {}}, {"id": "bielik-2.3", "tags": [], "timestamp": "22/12/2024,10:52:33", "results": {"art & entertainment": {"Accuracy": 58.0}, "culture & tradition": {"Accuracy": 61.0}, "geography": {"Accuracy": 68.0}, "grammar": {"Accuracy": 49.0}, "history": {"Accuracy": 76.0}, "vocab": {"Accuracy": 61.0}}, "columns": {}}, {"id": "llama-3.1-405b", "tags": [], "timestamp": "22/12/2024,10:57:48", "results": {"art & entertainment": {"Accuracy": 56.0}, "culture & tradition": {"Accuracy": 57.0}, "geography": {"Accuracy": 74.0}, "grammar": {"Accuracy": 57.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 43.0}}, "columns": {}}, {"id": "llama-3.1-70b", "tags": [], "timestamp": "22/12/2024,11:00:45", "results": {"art & entertainment": {"Accuracy": 42.0}, "culture & tradition": {"Accuracy": 41.0}, "geography": {"Accuracy": 58.0}, "grammar": {"Accuracy": 44.0}, "history": {"Accuracy": 68.0}, "vocab": {"Accuracy": 34.0}}, "columns": {}}, {"id": "llama-3.1-8b", "tags": [], "timestamp": "22/12/2024,11:02:01", "results": {"art & entertainment": {"Accuracy": 19.0}, "culture & tradition": {"Accuracy": 13.0}, "geography": {"Accuracy": 31.0}, "grammar": {"Accuracy": 29.0}, "history": {"Accuracy": 25.0}, "vocab": {"Accuracy": 19.0}}, "columns": {}}, {"id": "llama-3.3-70b", "tags": [], "timestamp": "22/12/2024,11:05:03", "results": {"art & entertainment": {"Accuracy": 43.0}, "culture & tradition": {"Accuracy": 40.0}, "geography": {"Accuracy": 59.0}, "grammar": {"Accuracy": 49.0}, "history": {"Accuracy": 65.0}, "vocab": {"Accuracy": 37.0}}, "columns": {}}, {"id": "claude-3-5-haiku-20241022", "tags": [], "timestamp": "22/12/2024,11:07:51", "results": {"art & entertainment": {"Accuracy": 43.0}, "culture & tradition": {"Accuracy": 62.0}, "geography": {"Accuracy": 72.0}, "grammar": {"Accuracy": 57.0}, "history": {"Accuracy": 61.0}, "vocab": {"Accuracy": 52.0}}, "columns": {}}, {"id": "claude-3-opus", "tags": [], "timestamp": "22/12/2024,11:15:30", "results": {"art & entertainment": {"Accuracy": 73.0}, "culture & tradition": {"Accuracy": 76.0}, "geography": {"Accuracy": 80.0}, "grammar": {"Accuracy": 66.0}, "history": {"Accuracy": 86.0}, "vocab": {"Accuracy": 62.0}}, "columns": {}}, {"id": "claude-3.5-sonnet", "tags": [], "timestamp": "22/12/2024,11:19:04", "results": {"art & entertainment": {"Accuracy": 77.0}, "culture & tradition": {"Accuracy": 87.0}, "geography": {"Accuracy": 85.0}, "grammar": {"Accuracy": 79.0}, "history": {"Accuracy": 91.0}, "vocab": {"Accuracy": 77.0}}, "columns": {}}, {"id": "ministral-8b", "tags": [], "timestamp": "22/12/2024,11:23:22", "results": {"art & entertainment": {"Accuracy": 14.0}, "culture & tradition": {"Accuracy": 12.0}, "geography": {"Accuracy": 19.0}, "grammar": {"Accuracy": 24.0}, "history": {"Accuracy": 33.0}, "vocab": {"Accuracy": 22.0}}, "columns": {}}, {"id": "mistral-7b-v0.3", "tags": [], "timestamp": "22/12/2024,11:26:27", "results": {"art & entertainment": {"Accuracy": 22.0}, "culture & tradition": {"Accuracy": 9.0}, "geography": {"Accuracy": 27.0}, "grammar": {"Accuracy": 27.0}, "history": {"Accuracy": 30.0}, "vocab": {"Accuracy": 16.0}}, "columns": {}}, {"id": "mistral-large-2407", "tags": [], "timestamp": "22/12/2024,11:32:53", "results": {"art & entertainment": {"Accuracy": 48.0}, "culture & tradition": {"Accuracy": 52.0}, "geography": {"Accuracy": 63.0}, "grammar": {"Accuracy": 51.0}, "history": {"Accuracy": 71.0}, "vocab": {"Accuracy": 40.0}}, "columns": {}}, {"id": "mistral-large-2411", "tags": [], "timestamp": "22/12/2024,11:38:26", "results": {"art & entertainment": {"Accuracy": 39.0}, "culture & tradition": {"Accuracy": 52.0}, "geography": {"Accuracy": 61.0}, "grammar": {"Accuracy": 54.0}, "history": {"Accuracy": 64.0}, "vocab": {"Accuracy": 42.0}}, "columns": {}}, {"id": "mistral-nemo", "tags": [], "timestamp": "22/12/2024,11:48:03", "results": {"art & entertainment": {"Accuracy": 20.0}, "culture & tradition": {"Accuracy": 13.0}, "geography": {"Accuracy": 26.0}, "grammar": {"Accuracy": 31.0}, "history": {"Accuracy": 28.0}, "vocab": {"Accuracy": 20.0}}, "columns": {}}, {"id": "mixtral-8x22b-instruct", "tags": [], "timestamp": "22/12/2024,11:50:55", "results": {"art & entertainment": {"Accuracy": 45.0}, "culture & tradition": {"Accuracy": 41.0}, "geography": {"Accuracy": 59.0}, "grammar": {"Accuracy": 50.0}, "history": {"Accuracy": 69.0}, "vocab": {"Accuracy": 35.0}}, "columns": {}}, {"id": "wizardlm-2-8x22b", "tags": [], "timestamp": "22/12/2024,11:56:55", "results": {"art & entertainment": {"Accuracy": 45.0}, "culture & tradition": {"Accuracy": 50.0}, "geography": {"Accuracy": 60.0}, "grammar": {"Accuracy": 49.0}, "history": {"Accuracy": 67.0}, "vocab": {"Accuracy": 38.0}}, "columns": {}}, {"id": "gpt-3.5-turbo", "tags": [], "timestamp": "22/12/2024,11:57:48", "results": {"art & entertainment": {"Accuracy": 39.0}, "culture & tradition": {"Accuracy": 38.0}, "geography": {"Accuracy": 55.0}, "grammar": {"Accuracy": 41.0}, "history": {"Accuracy": 51.0}, "vocab": {"Accuracy": 36.0}}, "columns": {}}, {"id": "gpt-4-turbo", "tags": [], "timestamp": "22/12/2024,12:01:34", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 74.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 56.0}, "history": {"Accuracy": 76.0}, "vocab": {"Accuracy": 56.0}}, "columns": {}}, {"id": "gpt-4o-2024-05-13", "tags": [], "timestamp": "22/12/2024,12:11:29", "results": {"art & entertainment": {"Accuracy": 83.0}, "culture & tradition": {"Accuracy": 92.0}, "geography": {"Accuracy": 89.0}, "grammar": {"Accuracy": 70.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 78.0}}, "columns": {}}, {"id": "gpt-4o-2024-08-06", "tags": [], "timestamp": "22/12/2024,12:12:02", "results": {"art & entertainment": {"Accuracy": 82.0}, "culture & tradition": {"Accuracy": 89.0}, "geography": {"Accuracy": 88.0}, "grammar": {"Accuracy": 66.0}, "history": {"Accuracy": 86.0}, "vocab": {"Accuracy": 77.0}}, "columns": {}}, {"id": "gpt-4o-2024-11-20", "tags": [], "timestamp": "22/12/2024,12:12:40", "results": {"art & entertainment": {"Accuracy": 82.0}, "culture & tradition": {"Accuracy": 89.0}, "geography": {"Accuracy": 86.0}, "grammar": {"Accuracy": 67.0}, "history": {"Accuracy": 84.0}, "vocab": {"Accuracy": 80.0}}, "columns": {}}, {"id": "gpt-4o-mini-2024-07-18", "tags": [], "timestamp": "22/12/2024,12:13:24", "results": {"art & entertainment": {"Accuracy": 42.0}, "culture & tradition": {"Accuracy": 57.0}, "geography": {"Accuracy": 69.0}, "grammar": {"Accuracy": 55.0}, "history": {"Accuracy": 67.0}, "vocab": {"Accuracy": 51.0}}, "columns": {}}, {"id": "gpt-4", "tags": [], "timestamp": "22/12/2024,12:16:44", "results": {"art & entertainment": {"Accuracy": 49.0}, "culture & tradition": {"Accuracy": 63.0}, "geography": {"Accuracy": 67.0}, "grammar": {"Accuracy": 58.0}, "history": {"Accuracy": 72.0}, "vocab": {"Accuracy": 48.0}}, "columns": {}}, {"id": "gemma-2-27b", "tags": [], "timestamp": "22/12/2024,12:20:37", "results": {"art & entertainment": {"Accuracy": 32.0}, "culture & tradition": {"Accuracy": 41.0}, "geography": {"Accuracy": 47.0}, "grammar": {"Accuracy": 46.0}, "history": {"Accuracy": 53.0}, "vocab": {"Accuracy": 37.0}}, "columns": {}}, {"id": "gemma-2-9b", "tags": [], "timestamp": "22/12/2024,12:21:43", "results": {"art & entertainment": {"Accuracy": 19.0}, "culture & tradition": {"Accuracy": 23.0}, "geography": {"Accuracy": 30.0}, "grammar": {"Accuracy": 38.0}, "history": {"Accuracy": 35.0}, "vocab": {"Accuracy": 30.0}}, "columns": {}}, {"id": "qwen-2.5-72b", "tags": [], "timestamp": "22/12/2024,12:28:03", "results": {"art & entertainment": {"Accuracy": 25.0}, "culture & tradition": {"Accuracy": 30.0}, "geography": {"Accuracy": 45.0}, "grammar": {"Accuracy": 45.0}, "history": {"Accuracy": 54.0}, "vocab": {"Accuracy": 36.0}}, "columns": {}}, {"id": "qwen-2.5-7b", "tags": [], "timestamp": "22/12/2024,12:29:53", "results": {"art & entertainment": {"Accuracy": 5.0}, "culture & tradition": {"Accuracy": 11.0}, "geography": {"Accuracy": 17.0}, "grammar": {"Accuracy": 29.0}, "history": {"Accuracy": 23.0}, "vocab": {"Accuracy": 21.0}}, "columns": {}}, {"id": "command-r-plus-04-2024", "tags": [], "timestamp": "22/12/2024,12:53:53", "results": {"art & entertainment": {"Accuracy": 39.0}, "culture & tradition": {"Accuracy": 52.0}, "geography": {"Accuracy": 53.0}, "grammar": {"Accuracy": 45.0}, "history": {"Accuracy": 61.0}, "vocab": {"Accuracy": 46.0}}, "columns": {}}, {"id": "command-r-plus-08-2024", "tags": [], "timestamp": "22/12/2024,12:56:04", "results": {"art & entertainment": {"Accuracy": 44.0}, "culture & tradition": {"Accuracy": 49.0}, "geography": {"Accuracy": 61.0}, "grammar": {"Accuracy": 43.0}, "history": {"Accuracy": 61.0}, "vocab": {"Accuracy": 43.0}}, "columns": {}}, {"id": "command-r7b", "tags": [], "timestamp": "22/12/2024,12:57:25", "results": {"art & entertainment": {"Accuracy": 14.0}, "culture & tradition": {"Accuracy": 18.0}, "geography": {"Accuracy": 33.0}, "grammar": {"Accuracy": 23.0}, "history": {"Accuracy": 27.0}, "vocab": {"Accuracy": 22.0}}, "columns": {}}, {"id": "grok-2-1212", "tags": [], "timestamp": "22/12/2024,13:08:22", "results": {"art & entertainment": {"Accuracy": 57.0}, "culture & tradition": {"Accuracy": 67.0}, "geography": {"Accuracy": 77.0}, "grammar": {"Accuracy": 64.0}, "history": {"Accuracy": 74.0}, "vocab": {"Accuracy": 57.0}}, "columns": {}}, {"id": "llama-3.0-70b", "tags": [], "timestamp": "22/12/2024,17:43:14", "results": {"art & entertainment": {"Accuracy": 40.0}, "culture & tradition": {"Accuracy": 38.0}, "geography": {"Accuracy": 49.0}, "grammar": {"Accuracy": 45.0}, "history": {"Accuracy": 64.0}, "vocab": {"Accuracy": 22.0}}, "columns": {}}, {"id": "gemini-2.0-flash-experimental", "tags": [], "timestamp": "22/12/2024,18:29:36", "results": {"art & entertainment": {"Accuracy": 68.0}, "culture & tradition": {"Accuracy": 78.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 65.0}, "history": {"Accuracy": 83.0}, "vocab": {"Accuracy": 72.0}}, "columns": {}}, {"id": "gemini-exp-1206", "tags": [], "timestamp": "23/12/2024,07:43:35", "results": {"art & entertainment": {"Accuracy": 83.0}, "culture & tradition": {"Accuracy": 90.0}, "geography": {"Accuracy": 86.0}, "grammar": {"Accuracy": 69.0}, "history": {"Accuracy": 88.0}, "vocab": {"Accuracy": 82.0}}, "columns": {}}, {"id": "claude-3.5-sonnet-20240620", "tags": [], "timestamp": "23/12/2024,08:09:06", "results": {"art & entertainment": {"Accuracy": 73.0}, "culture & tradition": {"Accuracy": 85.0}, "geography": {"Accuracy": 86.0}, "grammar": {"Accuracy": 75.0}, "history": {"Accuracy": 89.0}, "vocab": {"Accuracy": 76.0}}, "columns": {}}, {"id": "claude-3-sonnet", "tags": [], "timestamp": "23/12/2024,08:13:46", "results": {"art & entertainment": {"Accuracy": 46.0}, "culture & tradition": {"Accuracy": 53.0}, "geography": {"Accuracy": 65.0}, "grammar": {"Accuracy": 56.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 46.0}}, "columns": {}}, {"id": "deepseek-v3", "tags": [], "timestamp": "27/12/2024,13:43:33", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 73.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 62.0}, "history": {"Accuracy": 77.0}, "vocab": {"Accuracy": 63.0}}, "columns": {}}, {"id": "gemini-pro-1.5", "tags": [], "timestamp": "30/12/2024,17:25:33", "results": {"art & entertainment": {"Accuracy": 62.0}, "culture & tradition": {"Accuracy": 77.0}, "geography": {"Accuracy": 74.0}, "grammar": {"Accuracy": 58.0}, "history": {"Accuracy": 79.0}, "vocab": {"Accuracy": 68.0}}, "columns": {}}, {"id": "gemini-flash-1.5", "tags": [], "timestamp": "30/12/2024,17:26:44", "results": {"art & entertainment": {"Accuracy": 33.0}, "culture & tradition": {"Accuracy": 41.0}, "geography": {"Accuracy": 61.0}, "grammar": {"Accuracy": 46.0}, "history": {"Accuracy": 51.0}, "vocab": {"Accuracy": 47.0}}, "columns": {}}, {"id": "mixtral-8x7b-instruct", "tags": [], "timestamp": "04/01/2025,09:53:20", "results": {"art & entertainment": {"Accuracy": 31.0}, "culture & tradition": {"Accuracy": 27.0}, "geography": {"Accuracy": 44.0}, "grammar": {"Accuracy": 34.0}, "history": {"Accuracy": 56.0}, "vocab": {"Accuracy": 20.0}}, "columns": {}}, {"id": "deepseek-r1", "tags": [], "timestamp": "21/01/2025,09:18:53", "results": {"art & entertainment": {"Accuracy": 66.0}, "culture & tradition": {"Accuracy": 75.0}, "geography": {"Accuracy": 84.0}, "grammar": {"Accuracy": 74.0}, "history": {"Accuracy": 85.0}, "vocab": {"Accuracy": 72.0}}, "columns": {}}, {"id": "phi-4", "tags": [], "timestamp": "10/01/2025,11:39:56", "results": {"art & entertainment": {"Accuracy": 23.0}, "culture & tradition": {"Accuracy": 17.0}, "geography": {"Accuracy": 35.0}, "grammar": {"Accuracy": 34.0}, "history": {"Accuracy": 40.0}, "vocab": {"Accuracy": 26.0}}, "columns": {}}, {"id": "Mistral-Small-24B-Instruct-2501", "tags": [], "timestamp": "30/01/2025,16:33:56", "results": {"art & entertainment": {"Accuracy": 33.0}, "culture & tradition": {"Accuracy": 29.0}, "geography": {"Accuracy": 42.0}, "grammar": {"Accuracy": 45.0}, "history": {"Accuracy": 49.0}, "vocab": {"Accuracy": 36.0}}, "columns": {}}, {"id": "gemini-2.0-flash-thinking-exp-01-21", "tags": [], "timestamp": "30/01/2025,20:22:44", "results": {"art & entertainment": {"Accuracy": 72.0}, "culture & tradition": {"Accuracy": 76.0}, "geography": {"Accuracy": 84.0}, "grammar": {"Accuracy": 68.0}, "history": {"Accuracy": 80.0}, "vocab": {"Accuracy": 69.0}}, "columns": {}}, {"id": "o1-mini-2024-09-12", "tags": [], "timestamp": "30/01/2025,21:44:34", "results": {"art & entertainment": {"Accuracy": 38.0}, "culture & tradition": {"Accuracy": 44.0}, "geography": {"Accuracy": 66.0}, "grammar": {"Accuracy": 61.0}, "history": {"Accuracy": 61.0}, "vocab": {"Accuracy": 40.0}}, "columns": {}}, {"id": "o1-2024-12-17", "tags": [], "timestamp": "30/01/2025,22:02:44", "results": {"art & entertainment": {"Accuracy": 86.0}, "culture & tradition": {"Accuracy": 92.0}, "geography": {"Accuracy": 95.0}, "grammar": {"Accuracy": 84.0}, "history": {"Accuracy": 90.0}, "vocab": {"Accuracy": 88.0}}, "columns": {}}, {"id": "o3-mini-2025-01-31", "tags": [], "timestamp": "01/02/2025,13:22:44", "results": {"art & entertainment": {"Accuracy": 46.0}, "culture & tradition": {"Accuracy": 51.0}, "geography": {"Accuracy": 78.0}, "grammar": {"Accuracy": 67.0}, "history": {"Accuracy": 67.0}, "vocab": {"Accuracy": 47.0}}, "columns": {}}, {"id": "qwen-turbo-2024-11-01", "tags": [], "timestamp": "01/02/2025,16:36:12", "results": {"art & entertainment": {"Accuracy": 15.0}, "culture & tradition": {"Accuracy": 20.0}, "geography": {"Accuracy": 30.0}, "grammar": {"Accuracy": 33.0}, "history": {"Accuracy": 42.0}, "vocab": {"Accuracy": 31.0}}, "columns": {}}, {"id": "qwen-plus", "tags": [], "timestamp": "01/02/2025,17:56:42", "results": {"art & entertainment": {"Accuracy": 26.0}, "culture & tradition": {"Accuracy": 32.0}, "geography": {"Accuracy": 42.0}, "grammar": {"Accuracy": 47.0}, "history": {"Accuracy": 46.0}, "vocab": {"Accuracy": 38.0}}, "columns": {}}, {"id": "qwen-max", "tags": [], "timestamp": "01/02/2025,19:07:51", "results": {"art & entertainment": {"Accuracy": 43.0}, "culture & tradition": {"Accuracy": 50.0}, "geography": {"Accuracy": 53.0}, "grammar": {"Accuracy": 51.0}, "history": {"Accuracy": 63.0}, "vocab": {"Accuracy": 45.0}}, "columns": {}}, {"id": "PLLuM-12B-nc-chat", "tags": [], "timestamp": "24/02/2025,11:07:51", "results": {"art & entertainment": {"Accuracy": 59.0}, "culture & tradition": {"Accuracy": 65.0}, "geography": {"Accuracy": 70.0}, "grammar": {"Accuracy": 41.0}, "history": {"Accuracy": 70.0}, "vocab": {"Accuracy": 52.0}}, "columns": {}}, {"id": "PLLuM-8x7B-nc-chat", "tags": [], "timestamp": "24/02/2025,11:24:21", "results": {"art & entertainment": {"Accuracy": 72.0}, "culture & tradition": {"Accuracy": 76.0}, "geography": {"Accuracy": 73.0}, "grammar": {"Accuracy": 47.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 68.0}}, "columns": {}}, {"id": "llama-3.1-tulu-3-405b", "tags": [], "timestamp": "21/02/2025,08:53:23", "results": {"art & entertainment": {"Accuracy": 64.0}, "culture & tradition": {"Accuracy": 64.0}, "geography": {"Accuracy": 71.0}, "grammar": {"Accuracy": 56.0}, "history": {"Accuracy": 75.0}, "vocab": {"Accuracy": 53.0}}, "columns": {}}, {"id": "claude-3.7-sonnet", "tags": [], "timestamp": "24/02/2025,21:02:36", "results": {"art & entertainment": {"Accuracy": 80.0}, "culture & tradition": {"Accuracy": 83.0}, "geography": {"Accuracy": 87.0}, "grammar": {"Accuracy": 74.0}, "history": {"Accuracy": 90.0}, "vocab": {"Accuracy": 75.0}}, "columns": {}}, {"id": "EuroLLM-9B", "tags": [], "timestamp": "26/02/2025,17:48:49", "results": {"art & entertainment": {"Accuracy": 30.0}, "culture & tradition": {"Accuracy": 40.0}, "geography": {"Accuracy": 54.0}, "grammar": {"Accuracy": 39.0}, "history": {"Accuracy": 49.0}, "vocab": {"Accuracy": 34.0}}, "columns": {}}, {"id": "qwen-2.5-14B", "tags": [], "timestamp": "26/02/2025,17:56:50", "results": {"art & entertainment": {"Accuracy": 21.0}, "culture & tradition": {"Accuracy": 17.0}, "geography": {"Accuracy": 23.0}, "grammar": {"Accuracy": 34.0}, "history": {"Accuracy": 37.0}, "vocab": {"Accuracy": 28.0}}, "columns": {}}, {"id": "qwen-2.5-32B", "tags": [], "timestamp": "26/02/2025,18:08:53", "results": {"art & entertainment": {"Accuracy": 17.0}, "culture & tradition": {"Accuracy": 21.0}, "geography": {"Accuracy": 25.0}, "grammar": {"Accuracy": 43.0}, "history": {"Accuracy": 44.0}, "vocab": {"Accuracy": 33.0}}, "columns": {}}, {"id": "Llama-PLLuM-8B-chat", "tags": [], "timestamp": "26/02/2025,18:13:15", "results": {"art & entertainment": {"Accuracy": 33.0}, "culture & tradition": {"Accuracy": 34.0}, "geography": {"Accuracy": 46.0}, "grammar": {"Accuracy": 33.0}, "history": {"Accuracy": 50.0}, "vocab": {"Accuracy": 35.0}}, "columns": {}}, {"id": "PLLuM-12B-chat", "tags": [], "timestamp": "26/02/2025,18:18:29", "results": {"art & entertainment": {"Accuracy": 48.0}, "culture & tradition": {"Accuracy": 49.0}, "geography": {"Accuracy": 54.0}, "grammar": {"Accuracy": 37.0}, "history": {"Accuracy": 61.0}, "vocab": {"Accuracy": 33.0}}, "columns": {}}, {"id": "claude-3.7-sonnet-thinking", "tags": [], "timestamp": "27/02/2025,20:46:05", "results": {"art & entertainment": {"Accuracy": 77.0}, "culture & tradition": {"Accuracy": 82.0}, "geography": {"Accuracy": 87.0}, "grammar": {"Accuracy": 80.0}, "history": {"Accuracy": 92.0}, "vocab": {"Accuracy": 75.0}}, "columns": {}}, {"id": "gpt-4.5-preview-2025-02-27", "tags": [], "timestamp": "28/02/2025,07:25:40", "results": {"art & entertainment": {"Accuracy": 90.0}, "culture & tradition": {"Accuracy": 92.0}, "geography": {"Accuracy": 90.0}, "grammar": {"Accuracy": 74.0}, "history": {"Accuracy": 90.0}, "vocab": {"Accuracy": 83.0}}, "columns": {}}, {"id": "Llama-PLLuM-70B-chat", "tags": [], "timestamp": "04/03/2025,19:50:44", "results": {"art & entertainment": {"Accuracy": 49.0}, "culture & tradition": {"Accuracy": 64.0}, "geography": {"Accuracy": 68.0}, "grammar": {"Accuracy": 50.0}, "history": {"Accuracy": 74.0}, "vocab": {"Accuracy": 46.0}}, "columns": {}}, {"id": "PLLuM-8x7B-chat", "tags": [], "timestamp": "05/03/2025,08:21:34", "results": {"art & entertainment": {"Accuracy": 45.0}, "culture & tradition": {"Accuracy": 60.0}, "geography": {"Accuracy": 66.0}, "grammar": {"Accuracy": 42.0}, "history": {"Accuracy": 68.0}, "vocab": {"Accuracy": 44.0}}, "columns": {}}, {"id": "gemma-3-27b", "tags": [], "timestamp": "12/03/2025,18:25:52", "results": {"art & entertainment": {"Accuracy": 43.0}, "culture & tradition": {"Accuracy": 55.0}, "geography": {"Accuracy": 51.0}, "grammar": {"Accuracy": 46.0}, "history": {"Accuracy": 52.0}, "vocab": {"Accuracy": 37.0}}, "columns": {}}, {"id": "command-a-03-2025", "tags": [], "timestamp": "13/03/2025,22:20:56", "results": {"art & entertainment": {"Accuracy": 44.0}, "culture & tradition": {"Accuracy": 55.0}, "geography": {"Accuracy": 67.0}, "grammar": {"Accuracy": 49.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 49.0}}, "columns": {}}, {"id": "mistral-small-3.1-24b-2503", "tags": [], "timestamp": "17/03/2025,21:07:34", "results": {"art & entertainment": {"Accuracy": 35.0}, "culture & tradition": {"Accuracy": 39.0}, "geography": {"Accuracy": 45.0}, "grammar": {"Accuracy": 50.0}, "history": {"Accuracy": 54.0}, "vocab": {"Accuracy": 37.0}}, "columns": {}}, {"id": "deepseek-v3-0324", "tags": [], "timestamp": "24/03/2025,20:28:05", "results": {"art & entertainment": {"Accuracy": 64.0}, "culture & tradition": {"Accuracy": 76.0}, "geography": {"Accuracy": 78.0}, "grammar": {"Accuracy": 64.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 62.0}}, "columns": {}}, {"id": "gemini-2.5-pro-exp-03-25", "tags": [], "timestamp": "26/03/2025,14:13:03", "results": {"art & entertainment": {"Accuracy": 88.0}, "culture & tradition": {"Accuracy": 91.0}, "geography": {"Accuracy": 97.0}, "grammar": {"Accuracy": 79.0}, "history": {"Accuracy": 92.0}, "vocab": {"Accuracy": 90.0}}, "columns": {}}, {"id": "llama-4-maverick", "tags": [], "timestamp": "07/04/2025,08:06:41", "results": {"art & entertainment": {"Accuracy": 46.0}, "culture & tradition": {"Accuracy": 52.0}, "geography": {"Accuracy": 71.0}, "grammar": {"Accuracy": 59.0}, "history": {"Accuracy": 76.0}, "vocab": {"Accuracy": 45.0}}, "columns": {}}, {"id": "llama-4-scout", "tags": [], "timestamp": "05/04/2025,21:48:19", "results": {"art & entertainment": {"Accuracy": 23.0}, "culture & tradition": {"Accuracy": 35.0}, "geography": {"Accuracy": 51.0}, "grammar": {"Accuracy": 51.0}, "history": {"Accuracy": 47.0}, "vocab": {"Accuracy": 42.0}}, "columns": {}}, {"id": "grok-3", "tags": [], "timestamp": "10/04/2025,17:06:08", "results": {"art & entertainment": {"Accuracy": 71.0}, "culture & tradition": {"Accuracy": 90.0}, "geography": {"Accuracy": 83.0}, "grammar": {"Accuracy": 65.0}, "history": {"Accuracy": 85.0}, "vocab": {"Accuracy": 69.0}}, "columns": {}}, {"id": "grok-3-mini", "tags": [], "timestamp": "10/04/2025,17:26:00", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 67.0}, "geography": {"Accuracy": 84.0}, "grammar": {"Accuracy": 71.0}, "history": {"Accuracy": 84.0}, "vocab": {"Accuracy": 61.0}}, "columns": {}}, {"id": "gpt-4.1-2025-04-14", "tags": [], "timestamp": "14/04/2025,19:47:33", "results": {"art & entertainment": {"Accuracy": 77.0}, "culture & tradition": {"Accuracy": 84.0}, "geography": {"Accuracy": 89.0}, "grammar": {"Accuracy": 67.0}, "history": {"Accuracy": 85.0}, "vocab": {"Accuracy": 80.0}}, "columns": {}}, {"id": "gpt-4.1-mini-2025-04-14", "tags": [], "timestamp": "14/04/2025,19:51:14", "results": {"art & entertainment": {"Accuracy": 51.0}, "culture & tradition": {"Accuracy": 62.0}, "geography": {"Accuracy": 75.0}, "grammar": {"Accuracy": 62.0}, "history": {"Accuracy": 67.0}, "vocab": {"Accuracy": 56.0}}, "columns": {}}, {"id": "gpt-4.1-nano-2025-04-14", "tags": [], "timestamp": "14/04/2025,19:52:17", "results": {"art & entertainment": {"Accuracy": 30.0}, "culture & tradition": {"Accuracy": 40.0}, "geography": {"Accuracy": 59.0}, "grammar": {"Accuracy": 45.0}, "history": {"Accuracy": 50.0}, "vocab": {"Accuracy": 38.0}}, "columns": {}}, {"id": "o4-mini-2025-04-16", "tags": [], "timestamp": "16/04/2025,20:29:48", "results": {"art & entertainment": {"Accuracy": 62.0}, "culture & tradition": {"Accuracy": 73.0}, "geography": {"Accuracy": 88.0}, "grammar": {"Accuracy": 72.0}, "history": {"Accuracy": 77.0}, "vocab": {"Accuracy": 65.0}}, "columns": {}}, {"id": "o3-2025-04-16", "tags": [], "timestamp": "16/04/2025,20:54:41", "results": {"art & entertainment": {"Accuracy": 83.0}, "culture & tradition": {"Accuracy": 91.0}, "geography": {"Accuracy": 97.0}, "grammar": {"Accuracy": 85.0}, "history": {"Accuracy": 89.0}, "vocab": {"Accuracy": 90.0}}, "columns": {}}, {"id": "gemini-2.5-flash-preview-04-17", "tags": [], "timestamp": "18/04/2025,11:45:29", "results": {"art & entertainment": {"Accuracy": 78.0}, "culture & tradition": {"Accuracy": 85.0}, "geography": {"Accuracy": 94.0}, "grammar": {"Accuracy": 77.0}, "history": {"Accuracy": 86.0}, "vocab": {"Accuracy": 81.0}}, "columns": {}}, {"id": "qwen3-235b-a22b", "tags": [], "timestamp": "29/04/2025,19:22:53", "results": {"art & entertainment": {"Accuracy": 37.0}, "culture & tradition": {"Accuracy": 45.0}, "geography": {"Accuracy": 69.0}, "grammar": {"Accuracy": 66.0}, "history": {"Accuracy": 70.0}, "vocab": {"Accuracy": 43.0}}, "columns": {}}, {"id": "qwen3-30b-a3b", "tags": [], "timestamp": "29/04/2025,19:41:06", "results": {"art & entertainment": {"Accuracy": 19.0}, "culture & tradition": {"Accuracy": 30.0}, "geography": {"Accuracy": 31.0}, "grammar": {"Accuracy": 49.0}, "history": {"Accuracy": 42.0}, "vocab": {"Accuracy": 27.0}}, "columns": {}}, {"id": "qwen3-8b", "tags": [], "timestamp": "29/04/2025,14:56:27", "results": {"art & entertainment": {"Accuracy": 12.0}, "culture & tradition": {"Accuracy": 13.0}, "geography": {"Accuracy": 27.0}, "grammar": {"Accuracy": 38.0}, "history": {"Accuracy": 41.0}, "vocab": {"Accuracy": 25.0}}, "columns": {}}, {"id": "qwen3-32b", "tags": [], "timestamp": "29/04/2025,17:18:12", "results": {"art & entertainment": {"Accuracy": 21.0}, "culture & tradition": {"Accuracy": 28.0}, "geography": {"Accuracy": 37.0}, "grammar": {"Accuracy": 48.0}, "history": {"Accuracy": 55.0}, "vocab": {"Accuracy": 37.0}}, "columns": {}}, {"id": "qwen3-14b", "tags": [], "timestamp": "29/04/2025,11:46:36", "results": {"art & entertainment": {"Accuracy": 14.0}, "culture & tradition": {"Accuracy": 16.0}, "geography": {"Accuracy": 30.0}, "grammar": {"Accuracy": 46.0}, "history": {"Accuracy": 42.0}, "vocab": {"Accuracy": 34.0}}, "columns": {}}, {"id": "mistral-medium-3", "tags": [], "timestamp": "07/05/2025,17:57:20", "results": {"art & entertainment": {"Accuracy": 56.0}, "culture & tradition": {"Accuracy": 67.0}, "geography": {"Accuracy": 77.0}, "grammar": {"Accuracy": 61.0}, "history": {"Accuracy": 78.0}, "vocab": {"Accuracy": 62.0}}, "columns": {}}, {"id": "bielik-3-4.5b", "tags": [], "timestamp": "08/05/2025,08:33:49", "results": {"art & entertainment": {"Accuracy": 28.0}, "culture & tradition": {"Accuracy": 44.0}, "geography": {"Accuracy": 53.0}, "grammar": {"Accuracy": 35.0}, "history": {"Accuracy": 55.0}, "vocab": {"Accuracy": 39.0}}, "columns": {}}, {"id": "bielik-3-1.5b", "tags": [], "timestamp": "08/05/2025,08:37:56", "results": {"art & entertainment": {"Accuracy": 27.0}, "culture & tradition": {"Accuracy": 25.0}, "geography": {"Accuracy": 35.0}, "grammar": {"Accuracy": 23.0}, "history": {"Accuracy": 32.0}, "vocab": {"Accuracy": 23.0}}, "columns": {}}, {"id": "claude-4-sonnet", "tags": [], "timestamp": "23/05/2025,07:12:20", "results": {"art & entertainment": {"Accuracy": 55.0}, "culture & tradition": {"Accuracy": 72.0}, "geography": {"Accuracy": 77.0}, "grammar": {"Accuracy": 63.0}, "history": {"Accuracy": 81.0}, "vocab": {"Accuracy": 61.0}}, "columns": {}}, {"id": "claude-4-opus", "tags": [], "timestamp": "23/05/2025,09:42:39", "results": {"art & entertainment": {"Accuracy": 72.0}, "culture & tradition": {"Accuracy": 81.0}, "geography": {"Accuracy": 83.0}, "grammar": {"Accuracy": 76.0}, "history": {"Accuracy": 87.0}, "vocab": {"Accuracy": 73.0}}, "columns": {}}, {"id": "deepseek-r1-0528", "tags": [], "timestamp": "29/05/2025,12:33:05", "results": {"art & entertainment": {"Accuracy": 65.0}, "culture & tradition": {"Accuracy": 75.0}, "geography": {"Accuracy": 85.0}, "grammar": {"Accuracy": 73.0}, "history": {"Accuracy": 91.0}, "vocab": {"Accuracy": 68.0}}, "columns": {}}, {"id": "gemini-2.5-pro-preview-06-05", "tags": [], "timestamp": "08/06/2025,18:51:01", "results": {"art & entertainment": {"Accuracy": 91.0}, "culture & tradition": {"Accuracy": 96.0}, "geography": {"Accuracy": 98.0}, "grammar": {"Accuracy": 86.0}, "history": {"Accuracy": 92.0}, "vocab": {"Accuracy": 90.0}}, "columns": {}}, {"id": "bielik-2.6", "tags": [], "timestamp": "08/06/2025,21:15:14", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 68.0}, "geography": {"Accuracy": 75.0}, "grammar": {"Accuracy": 55.0}, "history": {"Accuracy": 72.0}, "vocab": {"Accuracy": 62.0}}, "columns": {}}, {"id": "bielik-2.5", "tags": [], "timestamp": "10/06/2025,16:33:14", "results": {"art & entertainment": {"Accuracy": 52.0}, "culture & tradition": {"Accuracy": 61.0}, "geography": {"Accuracy": 72.0}, "grammar": {"Accuracy": 51.0}, "history": {"Accuracy": 75.0}, "vocab": {"Accuracy": 61.0}}, "columns": {}}, {"id": "mistral-small-3.2-24b-2506", "tags": [], "timestamp": "20/06/2025,19:05:10", "results": {"art & entertainment": {"Accuracy": 38.0}, "culture & tradition": {"Accuracy": 39.0}, "geography": {"Accuracy": 51.0}, "grammar": {"Accuracy": 53.0}, "history": {"Accuracy": 61.0}, "vocab": {"Accuracy": 35.0}}, "columns": {}}, {"id": "magistral-small-2506", "tags": [], "timestamp": "20/06/2025,19:42:24", "results": {"art & entertainment": {"Accuracy": 30.0}, "culture & tradition": {"Accuracy": 29.0}, "geography": {"Accuracy": 45.0}, "grammar": {"Accuracy": 47.0}, "history": {"Accuracy": 54.0}, "vocab": {"Accuracy": 31.0}}, "columns": {}}, {"id": "grok-4", "tags": [], "timestamp": "10/07/2025,09:31:30", "results": {"art & entertainment": {"Accuracy": 86.0}, "culture & tradition": {"Accuracy": 95.0}, "geography": {"Accuracy": 94.0}, "grammar": {"Accuracy": 90.0}, "history": {"Accuracy": 94.0}, "vocab": {"Accuracy": 84.0}}, "columns": {}}, {"id": "kimi-k2", "tags": [], "timestamp": "13/07/2025,11:35:41", "results": {"art & entertainment": {"Accuracy": 50.0}, "culture & tradition": {"Accuracy": 67.0}, "geography": {"Accuracy": 70.0}, "grammar": {"Accuracy": 58.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 54.0}}, "columns": {}}, {"id": "pllum-12b-nc-chat-250715", "tags": [], "timestamp": "16/07/2025,15:45:55", "results": {"art & entertainment": {"Accuracy": 72.0}, "culture & tradition": {"Accuracy": 75.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 52.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 67.0}}, "columns": {}}, {"id": "Llama-PLLuM-70B-chat-250801", "tags": [], "timestamp": "01/08/2025,15:40:22", "results": {"art & entertainment": {"Accuracy": 54.0}, "culture & tradition": {"Accuracy": 62.0}, "geography": {"Accuracy": 63.0}, "grammar": {"Accuracy": 54.0}, "history": {"Accuracy": 69.0}, "vocab": {"Accuracy": 46.0}}, "columns": {}}, {"id": "glm-4.5", "tags": [], "timestamp": "03/08/2025,10:02:12", "results": {"art & entertainment": {"Accuracy": 56.0}, "culture & tradition": {"Accuracy": 68.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 59.0}, "history": {"Accuracy": 77.0}, "vocab": {"Accuracy": 60.0}}, "columns": {}}, {"id": "glm-4.5-air", "tags": [], "timestamp": "03/08/2025,10:09:10", "results": {"art & entertainment": {"Accuracy": 48.0}, "culture & tradition": {"Accuracy": 51.0}, "geography": {"Accuracy": 64.0}, "grammar": {"Accuracy": 52.0}, "history": {"Accuracy": 66.0}, "vocab": {"Accuracy": 47.0}}, "columns": {}}, {"id": "gpt-oss-120b", "tags": [], "timestamp": "05/08/2025,21:27:51", "results": {"art & entertainment": {"Accuracy": 42.0}, "culture & tradition": {"Accuracy": 46.0}, "geography": {"Accuracy": 71.0}, "grammar": {"Accuracy": 64.0}, "history": {"Accuracy": 65.0}, "vocab": {"Accuracy": 38.0}}, "columns": {}}, {"id": "gpt-oss-20b", "tags": [], "timestamp": "05/08/2025,21:46:32", "results": {"art & entertainment": {"Accuracy": 19.0}, "culture & tradition": {"Accuracy": 26.0}, "geography": {"Accuracy": 35.0}, "grammar": {"Accuracy": 54.0}, "history": {"Accuracy": 37.0}, "vocab": {"Accuracy": 23.0}}, "columns": {}}, {"id": "claude-opus-4.1", "tags": [], "timestamp": "06/08/2025,07:25:14", "results": {"art & entertainment": {"Accuracy": 67.0}, "culture & tradition": {"Accuracy": 83.0}, "geography": {"Accuracy": 86.0}, "grammar": {"Accuracy": 74.0}, "history": {"Accuracy": 91.0}, "vocab": {"Accuracy": 73.0}}, "columns": {}}, {"id": "gpt-5-2025-08-07", "tags": [], "timestamp": "07/08/2025,20:34:30", "results": {"art & entertainment": {"Accuracy": 85.0}, "culture & tradition": {"Accuracy": 89.0}, "geography": {"Accuracy": 97.0}, "grammar": {"Accuracy": 84.0}, "history": {"Accuracy": 91.0}, "vocab": {"Accuracy": 91.0}}, "columns": {}}, {"id": "gpt-5-mini-2025-08-07", "tags": [], "timestamp": "07/08/2025,20:42:02", "results": {"art & entertainment": {"Accuracy": 62.0}, "culture & tradition": {"Accuracy": 74.0}, "geography": {"Accuracy": 94.0}, "grammar": {"Accuracy": 82.0}, "history": {"Accuracy": 83.0}, "vocab": {"Accuracy": 70.0}}, "columns": {}}, {"id": "gpt-5-nano-2025-08-07", "tags": [], "timestamp": "07/08/2025,20:45:15", "results": {"art & entertainment": {"Accuracy": 47.0}, "culture & tradition": {"Accuracy": 59.0}, "geography": {"Accuracy": 80.0}, "grammar": {"Accuracy": 69.0}, "history": {"Accuracy": 73.0}, "vocab": {"Accuracy": 47.0}}, "columns": {}}, {"id": "deepseek-v3.1", "tags": [], "timestamp": "21/08/2025,19:24:33", "results": {"art & entertainment": {"Accuracy": 63.0}, "culture & tradition": {"Accuracy": 69.0}, "geography": {"Accuracy": 82.0}, "grammar": {"Accuracy": 64.0}, "history": {"Accuracy": 86.0}, "vocab": {"Accuracy": 62.0}}, "columns": {}}, {"id": "deepseek-v3.1-thinking", "tags": [], "timestamp": "21/08/2025,19:56:46", "results": {"art & entertainment": {"Accuracy": 69.0}, "culture & tradition": {"Accuracy": 76.0}, "geography": {"Accuracy": 89.0}, "grammar": {"Accuracy": 75.0}, "history": {"Accuracy": 89.0}, "vocab": {"Accuracy": 74.0}}, "columns": {}}, {"id": "qwen3-max", "tags": [], "timestamp": "05/09/2025,19:40:20", "results": {"art & entertainment": {"Accuracy": 50.0}, "culture & tradition": {"Accuracy": 57.0}, "geography": {"Accuracy": 75.0}, "grammar": {"Accuracy": 58.0}, "history": {"Accuracy": 74.0}, "vocab": {"Accuracy": 54.0}}, "columns": {}}, {"id": "kimi-k2-0905", "tags": [], "timestamp": "05/09/2025,20:00:33", "results": {"art & entertainment": {"Accuracy": 54.0}, "culture & tradition": {"Accuracy": 63.0}, "geography": {"Accuracy": 67.0}, "grammar": {"Accuracy": 59.0}, "history": {"Accuracy": 70.0}, "vocab": {"Accuracy": 53.0}}, "columns": {}}, {"id": "qwen3-next-80b-a3b-instruct", "tags": [], "timestamp": "12/09/2025,09:09:10", "results": {"art & entertainment": {"Accuracy": 34.0}, "culture & tradition": {"Accuracy": 36.0}, "geography": {"Accuracy": 46.0}, "grammar": {"Accuracy": 52.0}, "history": {"Accuracy": 58.0}, "vocab": {"Accuracy": 32.0}}, "columns": {}}, {"id": "qwen3-next-80b-a3b-thinking", "tags": [], "timestamp": "12/09/2025,10:27:07", "results": {"art & entertainment": {"Accuracy": 43.0}, "culture & tradition": {"Accuracy": 45.0}, "geography": {"Accuracy": 64.0}, "grammar": {"Accuracy": 65.0}, "history": {"Accuracy": 72.0}, "vocab": {"Accuracy": 37.0}}, "columns": {}}, {"id": "claude-sonnet-4.5", "tags": [], "timestamp": "30/09/2025,15:59:40", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 72.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 68.0}, "history": {"Accuracy": 85.0}, "vocab": {"Accuracy": 61.0}}, "columns": {}}, {"id": "deepseek-v3.2-exp", "tags": [], "timestamp": "30/09/2025,16:11:11", "results": {"art & entertainment": {"Accuracy": 59.0}, "culture & tradition": {"Accuracy": 71.0}, "geography": {"Accuracy": 80.0}, "grammar": {"Accuracy": 63.0}, "history": {"Accuracy": 83.0}, "vocab": {"Accuracy": 64.0}}, "columns": {}}, {"id": "glm-4.6", "tags": [], "timestamp": "01/10/2025,09:13:50", "results": {"art & entertainment": {"Accuracy": 59.0}, "culture & tradition": {"Accuracy": 76.0}, "geography": {"Accuracy": 82.0}, "grammar": {"Accuracy": 63.0}, "history": {"Accuracy": 87.0}, "vocab": {"Accuracy": 57.0}}, "columns": {}}, {"id": "grok-4-fast", "tags": [], "timestamp": "19/10/2025,17:43:58", "results": {"art & entertainment": {"Accuracy": 59.0}, "culture & tradition": {"Accuracy": 71.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 72.0}, "history": {"Accuracy": 81.0}, "vocab": {"Accuracy": 59.0}}, "columns": {}}, {"id": "claude-haiku-4.5", "tags": [], "timestamp": "19/10/2025,09:38:21", "results": {"art & entertainment": {"Accuracy": 36.0}, "culture & tradition": {"Accuracy": 52.0}, "geography": {"Accuracy": 52.0}, "grammar": {"Accuracy": 59.0}, "history": {"Accuracy": 60.0}, "vocab": {"Accuracy": 45.0}}, "columns": {}}, {"id": "gpt-5-pro-2025-10-06", "tags": [], "timestamp": "20/10/2025,11:29:36", "results": {"art & entertainment": {"Accuracy": 88.0}, "culture & tradition": {"Accuracy": 94.0}, "geography": {"Accuracy": 96.0}, "grammar": {"Accuracy": 85.0}, "history": {"Accuracy": 91.0}, "vocab": {"Accuracy": 92.0}}, "columns": {}}, {"id": "kimi-k2-thinking", "tags": [], "timestamp": "07/11/2025,19:54:56", "results": {"art & entertainment": {"Accuracy": 63.0}, "culture & tradition": {"Accuracy": 71.0}, "geography": {"Accuracy": 84.0}, "grammar": {"Accuracy": 73.0}, "history": {"Accuracy": 80.0}, "vocab": {"Accuracy": 59.0}}, "columns": {}}, {"id": "gpt-5.1-2025-11-13", "tags": [], "timestamp": "14/11/2025,08:43:34", "results": {"art & entertainment": {"Accuracy": 72.0}, "culture & tradition": {"Accuracy": 82.0}, "geography": {"Accuracy": 86.0}, "grammar": {"Accuracy": 70.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 75.0}}, "columns": {}}, {"id": "gpt-5.1-2025-11-13-high", "tags": [], "timestamp": "14/11/2025,09:27:30", "results": {"art & entertainment": {"Accuracy": 85.0}, "culture & tradition": {"Accuracy": 90.0}, "geography": {"Accuracy": 97.0}, "grammar": {"Accuracy": 82.0}, "history": {"Accuracy": 89.0}, "vocab": {"Accuracy": 90.0}}, "columns": {}}, {"id": "gemini-3.0-pro-preview", "tags": [], "timestamp": "19/11/2025,07:43:47", "results": {"art & entertainment": {"Accuracy": 95.0}, "culture & tradition": {"Accuracy": 99.0}, "geography": {"Accuracy": 100.0}, "grammar": {"Accuracy": 91.0}, "history": {"Accuracy": 95.0}, "vocab": {"Accuracy": 95.0}}, "columns": {}}, {"id": "grok-4.1-fast", "tags": [], "timestamp": "20/11/2025,17:39:08", "results": {"art & entertainment": {"Accuracy": 54.0}, "culture & tradition": {"Accuracy": 74.0}, "geography": {"Accuracy": 85.0}, "grammar": {"Accuracy": 72.0}, "history": {"Accuracy": 84.0}, "vocab": {"Accuracy": 65.0}}, "columns": {}}, {"id": "claude-opus-4.5", "tags": [], "timestamp": "27/11/2025,07:24:44", "results": {"art & entertainment": {"Accuracy": 74.0}, "culture & tradition": {"Accuracy": 82.0}, "geography": {"Accuracy": 84.0}, "grammar": {"Accuracy": 79.0}, "history": {"Accuracy": 87.0}, "vocab": {"Accuracy": 76.0}}, "columns": {}}, {"id": "deepseek-v3.2", "tags": [], "timestamp": "02/12/2025,07:57:06", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 78.0}, "geography": {"Accuracy": 78.0}, "grammar": {"Accuracy": 66.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 65.0}}, "columns": {}}, {"id": "deepseek-v3.2-speciale", "tags": [], "timestamp": "02/12/2025,08:16:07", "results": {"art & entertainment": {"Accuracy": 71.0}, "culture & tradition": {"Accuracy": 76.0}, "geography": {"Accuracy": 94.0}, "grammar": {"Accuracy": 84.0}, "history": {"Accuracy": 90.0}, "vocab": {"Accuracy": 71.0}}, "columns": {}}, {"id": "mistral-large-2512", "tags": [], "timestamp": "02/12/2025,17:57:56", "results": {"art & entertainment": {"Accuracy": 63.0}, "culture & tradition": {"Accuracy": 75.0}, "geography": {"Accuracy": 76.0}, "grammar": {"Accuracy": 67.0}, "history": {"Accuracy": 79.0}, "vocab": {"Accuracy": 64.0}}, "columns": {}}, {"id": "ministral-3b-2512", "tags": [], "timestamp": "07/12/2025,18:29:00", "results": {"art & entertainment": {"Accuracy": 11.0}, "culture & tradition": {"Accuracy": 17.0}, "geography": {"Accuracy": 24.0}, "grammar": {"Accuracy": 30.0}, "history": {"Accuracy": 30.0}, "vocab": {"Accuracy": 22.0}}, "columns": {}}, {"id": "ministral-8b-2512", "tags": [], "timestamp": "07/12/2025,18:31:29", "results": {"art & entertainment": {"Accuracy": 20.0}, "culture & tradition": {"Accuracy": 30.0}, "geography": {"Accuracy": 39.0}, "grammar": {"Accuracy": 44.0}, "history": {"Accuracy": 43.0}, "vocab": {"Accuracy": 35.0}}, "columns": {}}, {"id": "ministral-14b-2512", "tags": [], "timestamp": "07/12/2025,18:34:31", "results": {"art & entertainment": {"Accuracy": 25.0}, "culture & tradition": {"Accuracy": 29.0}, "geography": {"Accuracy": 45.0}, "grammar": {"Accuracy": 44.0}, "history": {"Accuracy": 52.0}, "vocab": {"Accuracy": 39.0}}, "columns": {}}, {"id": "gpt-5.2-2025-12-11", "tags": [], "timestamp": "11/12/2025,21:30:16", "results": {"art & entertainment": {"Accuracy": 74.0}, "culture & tradition": {"Accuracy": 84.0}, "geography": {"Accuracy": 94.0}, "grammar": {"Accuracy": 82.0}, "history": {"Accuracy": 90.0}, "vocab": {"Accuracy": 86.0}}, "columns": {}}, {"id": "gpt-5.2-2025-12-11-high", "tags": [], "timestamp": "11/12/2025,21:34:23", "results": {"art & entertainment": {"Accuracy": 78.0}, "culture & tradition": {"Accuracy": 87.0}, "geography": {"Accuracy": 95.0}, "grammar": {"Accuracy": 87.0}, "history": {"Accuracy": 90.0}, "vocab": {"Accuracy": 86.0}}, "columns": {}}, {"id": "gpt-5.2-2025-12-11-xhigh", "tags": [], "timestamp": "14/12/2025,10:54:01", "results": {"art & entertainment": {"Accuracy": 79.0}, "culture & tradition": {"Accuracy": 93.0}, "geography": {"Accuracy": 94.0}, "grammar": {"Accuracy": 89.0}, "history": {"Accuracy": 94.0}, "vocab": {"Accuracy": 87.0}}, "columns": {}}, {"id": "gpt-5.2-2025-12-11-no", "tags": [], "timestamp": "14/12/2025,10:57:01", "results": {"art & entertainment": {"Accuracy": 70.0}, "culture & tradition": {"Accuracy": 86.0}, "geography": {"Accuracy": 86.0}, "grammar": {"Accuracy": 69.0}, "history": {"Accuracy": 85.0}, "vocab": {"Accuracy": 77.0}}, "columns": {}}, {"id": "gemini-3-flash-preview", "tags": [], "timestamp": "19/12/2025,15:41:59", "results": {"art & entertainment": {"Accuracy": 91.0}, "culture & tradition": {"Accuracy": 98.0}, "geography": {"Accuracy": 96.0}, "grammar": {"Accuracy": 85.0}, "history": {"Accuracy": 92.0}, "vocab": {"Accuracy": 88.0}}, "columns": {}}, {"id": "glm-4.7", "tags": [], "timestamp": "23/12/2025,13:57:40", "results": {"art & entertainment": {"Accuracy": 64.0}, "culture & tradition": {"Accuracy": 79.0}, "geography": {"Accuracy": 88.0}, "grammar": {"Accuracy": 66.0}, "history": {"Accuracy": 85.0}, "vocab": {"Accuracy": 59.0}}, "columns": {}}, {"id": "Bielik-11B-v3.0-Instruct", "tags": [], "timestamp": "31/12/2025,13:39:24", "results": {"art & entertainment": {"Accuracy": 69.0}, "culture & tradition": {"Accuracy": 78.0}, "geography": {"Accuracy": 75.0}, "grammar": {"Accuracy": 57.0}, "history": {"Accuracy": 78.0}, "vocab": {"Accuracy": 67.0}}, "columns": {}}, {"id": "glm-4.7-flash", "tags": [], "timestamp": "20/01/2026,17:21:48", "results": {"art & entertainment": {"Accuracy": 31.0}, "culture & tradition": {"Accuracy": 40.0}, "geography": {"Accuracy": 55.0}, "grammar": {"Accuracy": 44.0}, "history": {"Accuracy": 54.0}, "vocab": {"Accuracy": 30.0}}, "columns": {}}, {"id": "kimi-k2.5", "tags": [], "timestamp": "27/01/2026,20:48:09", "results": {"art & entertainment": {"Accuracy": 69.0}, "culture & tradition": {"Accuracy": 78.0}, "geography": {"Accuracy": 86.0}, "grammar": {"Accuracy": 80.0}, "history": {"Accuracy": 89.0}, "vocab": {"Accuracy": 65.0}}, "columns": {}}, {"id": "claude-opus-4.6", "tags": [], "timestamp": "06/02/2026,08:32:41", "results": {"art & entertainment": {"Accuracy": 75.0}, "culture & tradition": {"Accuracy": 86.0}, "geography": {"Accuracy": 88.0}, "grammar": {"Accuracy": 77.0}, "history": {"Accuracy": 87.0}, "vocab": {"Accuracy": 78.0}}, "columns": {}}, {"id": "glm-5", "tags": [], "timestamp": "11/02/2026,19:00:12", "results": {"art & entertainment": {"Accuracy": 66.0}, "culture & tradition": {"Accuracy": 81.0}, "geography": {"Accuracy": 91.0}, "grammar": {"Accuracy": 82.0}, "history": {"Accuracy": 88.0}, "vocab": {"Accuracy": 72.0}}, "columns": {}}, {"id": "minimax-m2.5", "tags": [], "timestamp": "13/02/2026,15:27:56", "results": {"art & entertainment": {"Accuracy": 39.0}, "culture & tradition": {"Accuracy": 59.0}, "geography": {"Accuracy": 68.0}, "grammar": {"Accuracy": 71.0}, "history": {"Accuracy": 69.0}, "vocab": {"Accuracy": 52.0}}, "columns": {}}, {"id": "qwen3.5-397b-a17b", "tags": [], "timestamp": "16/02/2026,12:18:26", "results": {"art & entertainment": {"Accuracy": 63.0}, "culture & tradition": {"Accuracy": 73.0}, "geography": {"Accuracy": 85.0}, "grammar": {"Accuracy": 76.0}, "history": {"Accuracy": 83.0}, "vocab": {"Accuracy": 70.0}}, "columns": {}}, {"id": "claude-sonnet-4.6", "tags": [], "timestamp": "18/02/2026,07:45:10", "results": {"art & entertainment": {"Accuracy": 67.0}, "culture & tradition": {"Accuracy": 82.0}, "geography": {"Accuracy": 81.0}, "grammar": {"Accuracy": 80.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 74.0}}, "columns": {}}, {"id": "gemini-3.1-pro-preview", "tags": [], "timestamp": "20/02/2026,09:12:43", "results": {"art & entertainment": {"Accuracy": 95.0}, "culture & tradition": {"Accuracy": 100.0}, "geography": {"Accuracy": 100.0}, "grammar": {"Accuracy": 93.0}, "history": {"Accuracy": 98.0}, "vocab": {"Accuracy": 96.0}}, "columns": {}}, {"id": "Qwen3.5-35B-A3B", "tags": [], "timestamp": "25/02/2026,09:46:55", "results": {"art & entertainment": {"Accuracy": 44.0}, "culture & tradition": {"Accuracy": 46.0}, "geography": {"Accuracy": 73.0}, "grammar": {"Accuracy": 66.0}, "history": {"Accuracy": 68.0}, "vocab": {"Accuracy": 45.0}}, "columns": {}}, {"id": "Qwen3.5-122B-A10B", "tags": [], "timestamp": "25/02/2026,16:10:20", "results": {"art & entertainment": {"Accuracy": 53.0}, "culture & tradition": {"Accuracy": 62.0}, "geography": {"Accuracy": 83.0}, "grammar": {"Accuracy": 73.0}, "history": {"Accuracy": 78.0}, "vocab": {"Accuracy": 61.0}}, "columns": {}}, {"id": "Qwen3.5-27B", "tags": [], "timestamp": "25/02/2026,16:38:23", "results": {"art & entertainment": {"Accuracy": 37.0}, "culture & tradition": {"Accuracy": 46.0}, "geography": {"Accuracy": 64.0}, "grammar": {"Accuracy": 62.0}, "history": {"Accuracy": 63.0}, "vocab": {"Accuracy": 54.0}}, "columns": {}}, {"id": "Qwen3.5-2B", "tags": [], "timestamp": "02/03/2026,17:24:33", "results": {"art & entertainment": {"Accuracy": 5.0}, "culture & tradition": {"Accuracy": 13.0}, "geography": {"Accuracy": 12.0}, "grammar": {"Accuracy": 19.0}, "history": {"Accuracy": 14.0}, "vocab": {"Accuracy": 20.0}}, "columns": {}}, {"id": "Qwen3.5-9B", "tags": [], "timestamp": "02/03/2026,18:38:48", "results": {"art & entertainment": {"Accuracy": 22.0}, "culture & tradition": {"Accuracy": 36.0}, "geography": {"Accuracy": 44.0}, "grammar": {"Accuracy": 54.0}, "history": {"Accuracy": 48.0}, "vocab": {"Accuracy": 38.0}}, "columns": {}}, {"id": "Qwen3.5-4B", "tags": [], "timestamp": "02/03/2026,21:26:49", "results": {"art & entertainment": {"Accuracy": 12.0}, "culture & tradition": {"Accuracy": 24.0}, "geography": {"Accuracy": 27.0}, "grammar": {"Accuracy": 45.0}, "history": {"Accuracy": 36.0}, "vocab": {"Accuracy": 34.0}}, "columns": {}}, {"id": "gpt-5.4-2026-03-05-high", "tags": [], "timestamp": "06/03/2026,08:36:27", "results": {"art & entertainment": {"Accuracy": 91.0}, "culture & tradition": {"Accuracy": 93.0}, "geography": {"Accuracy": 96.0}, "grammar": {"Accuracy": 90.0}, "history": {"Accuracy": 92.0}, "vocab": {"Accuracy": 91.0}}, "columns": {}}, {"id": "gpt-5.4-2026-03-05-low", "tags": [], "timestamp": "06/03/2026,08:40:24", "results": {"art & entertainment": {"Accuracy": 87.0}, "culture & tradition": {"Accuracy": 93.0}, "geography": {"Accuracy": 97.0}, "grammar": {"Accuracy": 88.0}, "history": {"Accuracy": 93.0}, "vocab": {"Accuracy": 85.0}}, "columns": {}}, {"id": "gpt-5.4-2026-03-05-no", "tags": [], "timestamp": "06/03/2026,08:42:58", "results": {"art & entertainment": {"Accuracy": 79.0}, "culture & tradition": {"Accuracy": 88.0}, "geography": {"Accuracy": 88.0}, "grammar": {"Accuracy": 79.0}, "history": {"Accuracy": 87.0}, "vocab": {"Accuracy": 85.0}}, "columns": {}}, {"id": "Mistral-Small-4", "tags": [], "timestamp": "17/03/2026,13:18:22", "results": {"art & entertainment": {"Accuracy": 53.0}, "culture & tradition": {"Accuracy": 49.0}, "geography": {"Accuracy": 64.0}, "grammar": {"Accuracy": 56.0}, "history": {"Accuracy": 64.0}, "vocab": {"Accuracy": 52.0}}, "columns": {}}, {"id": "Bielik-Minitron-7B-v3.0-Instruct", "tags": [], "timestamp": "19/03/2026,09:35:18", "results": {"art & entertainment": {"Accuracy": 39.0}, "culture & tradition": {"Accuracy": 57.0}, "geography": {"Accuracy": 62.0}, "grammar": {"Accuracy": 50.0}, "history": {"Accuracy": 64.0}, "vocab": {"Accuracy": 46.0}}, "columns": {}}, {"id": "gpt-5.4-mini-2026-03-17-high", "tags": [], "timestamp": "20/03/2026,15:58:48", "results": {"art & entertainment": {"Accuracy": 76.0}, "culture & tradition": {"Accuracy": 83.0}, "geography": {"Accuracy": 92.0}, "grammar": {"Accuracy": 85.0}, "history": {"Accuracy": 89.0}, "vocab": {"Accuracy": 86.0}}, "columns": {}}, {"id": "gpt-5.4-mini-2026-03-17-no", "tags": [], "timestamp": "20/03/2026,15:59:46", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 73.0}, "geography": {"Accuracy": 82.0}, "grammar": {"Accuracy": 70.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 70.0}}, "columns": {}}, {"id": "gpt-5.4-nano-2026-03-17-high", "tags": [], "timestamp": "20/03/2026,16:03:16", "results": {"art & entertainment": {"Accuracy": 50.0}, "culture & tradition": {"Accuracy": 57.0}, "geography": {"Accuracy": 77.0}, "grammar": {"Accuracy": 74.0}, "history": {"Accuracy": 76.0}, "vocab": {"Accuracy": 61.0}}, "columns": {}}, {"id": "gpt-5.4-nano-2026-03-17-no", "tags": [], "timestamp": "20/03/2026,16:04:12", "results": {"art & entertainment": {"Accuracy": 26.0}, "culture & tradition": {"Accuracy": 44.0}, "geography": {"Accuracy": 52.0}, "grammar": {"Accuracy": 45.0}, "history": {"Accuracy": 57.0}, "vocab": {"Accuracy": 41.0}}, "columns": {}}, {"id": "mimo-v2-pro", "tags": [], "timestamp": "20/03/2026,16:30:12", "results": {"art & entertainment": {"Accuracy": 64.0}, "culture & tradition": {"Accuracy": 79.0}, "geography": {"Accuracy": 89.0}, "grammar": {"Accuracy": 79.0}, "history": {"Accuracy": 87.0}, "vocab": {"Accuracy": 73.0}}, "columns": {}}, {"id": "minimax-m2.7", "tags": [], "timestamp": "20/03/2026,17:28:18", "results": {"art & entertainment": {"Accuracy": 43.0}, "culture & tradition": {"Accuracy": 59.0}, "geography": {"Accuracy": 82.0}, "grammar": {"Accuracy": 72.0}, "history": {"Accuracy": 64.0}, "vocab": {"Accuracy": 60.0}}, "columns": {}}, {"id": "grok-4.20", "tags": [], "timestamp": "01/04/2026,16:25:27", "results": {"art & entertainment": {"Accuracy": 55.0}, "culture & tradition": {"Accuracy": 65.0}, "geography": {"Accuracy": 74.0}, "grammar": {"Accuracy": 72.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 59.0}}, "columns": {}}, {"id": "qwen3.6-plus", "tags": [], "timestamp": "02/04/2026,19:09:30", "results": {"art & entertainment": {"Accuracy": 61.0}, "culture & tradition": {"Accuracy": 68.0}, "geography": {"Accuracy": 90.0}, "grammar": {"Accuracy": 80.0}, "history": {"Accuracy": 86.0}, "vocab": {"Accuracy": 66.0}}, "columns": {}}, {"id": "gemma-4-E2B-it", "tags": [], "timestamp": "03/04/2026,08:44:06", "results": {"art & entertainment": {"Accuracy": 5.0}, "culture & tradition": {"Accuracy": 18.0}, "geography": {"Accuracy": 16.0}, "grammar": {"Accuracy": 25.0}, "history": {"Accuracy": 21.0}, "vocab": {"Accuracy": 22.0}}, "columns": {}}, {"id": "gemma-4-E4B-it", "tags": [], "timestamp": "03/04/2026,08:57:09", "results": {"art & entertainment": {"Accuracy": 14.0}, "culture & tradition": {"Accuracy": 29.0}, "geography": {"Accuracy": 28.0}, "grammar": {"Accuracy": 44.0}, "history": {"Accuracy": 32.0}, "vocab": {"Accuracy": 29.0}}, "columns": {}}, {"id": "gemma-4-26B-A4B-it", "tags": [], "timestamp": "03/04/2026,09:13:36", "results": {"art & entertainment": {"Accuracy": 42.0}, "culture & tradition": {"Accuracy": 62.0}, "geography": {"Accuracy": 64.0}, "grammar": {"Accuracy": 56.0}, "history": {"Accuracy": 62.0}, "vocab": {"Accuracy": 57.0}}, "columns": {}}, {"id": "gemma-4-31B-it", "tags": [], "timestamp": "03/04/2026,09:31:43", "results": {"art & entertainment": {"Accuracy": 49.0}, "culture & tradition": {"Accuracy": 63.0}, "geography": {"Accuracy": 62.0}, "grammar": {"Accuracy": 63.0}, "history": {"Accuracy": 62.0}, "vocab": {"Accuracy": 56.0}}, "columns": {}}, {"id": "glm-5.1", "tags": [], "timestamp": "07/04/2026,19:36:33", "results": {"art & entertainment": {"Accuracy": 68.0}, "culture & tradition": {"Accuracy": 80.0}, "geography": {"Accuracy": 94.0}, "grammar": {"Accuracy": 83.0}, "history": {"Accuracy": 84.0}, "vocab": {"Accuracy": 77.0}}, "columns": {}}, {"id": "claude-opus-4.7", "tags": [], "timestamp": "17/04/2026,11:41:40", "results": {"art & entertainment": {"Accuracy": 81.0}, "culture & tradition": {"Accuracy": 86.0}, "geography": {"Accuracy": 92.0}, "grammar": {"Accuracy": 88.0}, "history": {"Accuracy": 94.0}, "vocab": {"Accuracy": 85.0}}, "columns": {}}, {"id": "Qwen3.6-35B-A3B", "tags": [], "timestamp": "17/04/2026,13:00:38", "results": {"art & entertainment": {"Accuracy": 39.0}, "culture & tradition": {"Accuracy": 44.0}, "geography": {"Accuracy": 67.0}, "grammar": {"Accuracy": 67.0}, "history": {"Accuracy": 69.0}, "vocab": {"Accuracy": 44.0}}, "columns": {}}, {"id": "gemma-4-31B-it-reasoning", "tags": [], "timestamp": "18/04/2026,18:23:24", "results": {"art & entertainment": {"Accuracy": 53.0}, "culture & tradition": {"Accuracy": 67.0}, "geography": {"Accuracy": 74.0}, "grammar": {"Accuracy": 79.0}, "history": {"Accuracy": 75.0}, "vocab": {"Accuracy": 68.0}}, "columns": {}}, {"id": "gemma-4-26B-A4B-it-reasoning", "tags": [], "timestamp": "18/04/2026,19:44:24", "results": {"art & entertainment": {"Accuracy": 50.0}, "culture & tradition": {"Accuracy": 66.0}, "geography": {"Accuracy": 77.0}, "grammar": {"Accuracy": 79.0}, "history": {"Accuracy": 72.0}, "vocab": {"Accuracy": 67.0}}, "columns": {}}, {"id": "gemma-4-E4B-it-reasoning", "tags": [], "timestamp": "19/04/2026,07:34:46", "results": {"art & entertainment": {"Accuracy": 20.0}, "culture & tradition": {"Accuracy": 30.0}, "geography": {"Accuracy": 31.0}, "grammar": {"Accuracy": 46.0}, "history": {"Accuracy": 38.0}, "vocab": {"Accuracy": 31.0}}, "columns": {}}, {"id": "gemma-4-E2B-it-reasoning", "tags": [], "timestamp": "19/04/2026,07:54:42", "results": {"art & entertainment": {"Accuracy": 8.0}, "culture & tradition": {"Accuracy": 23.0}, "geography": {"Accuracy": 18.0}, "grammar": {"Accuracy": 44.0}, "history": {"Accuracy": 22.0}, "vocab": {"Accuracy": 25.0}}, "columns": {}}, {"id": "kimi-k2.6", "tags": [], "timestamp": "20/04/2026,21:19:12", "results": {"art & entertainment": {"Accuracy": 67.0}, "culture & tradition": {"Accuracy": 74.0}, "geography": {"Accuracy": 88.0}, "grammar": {"Accuracy": 82.0}, "history": {"Accuracy": 86.0}, "vocab": {"Accuracy": 68.0}}, "columns": {}}, {"id": "deepseek-v4-flash", "tags": [], "timestamp": "24/04/2026,07:18:20", "results": {"art & entertainment": {"Accuracy": 64.0}, "culture & tradition": {"Accuracy": 73.0}, "geography": {"Accuracy": 91.0}, "grammar": {"Accuracy": 81.0}, "history": {"Accuracy": 88.0}, "vocab": {"Accuracy": 78.0}}, "columns": {}}, {"id": "deepseek-v4-pro", "tags": [], "timestamp": "24/04/2026,07:47:13", "results": {"art & entertainment": {"Accuracy": 80.0}, "culture & tradition": {"Accuracy": 85.0}, "geography": {"Accuracy": 93.0}, "grammar": {"Accuracy": 92.0}, "history": {"Accuracy": 93.0}, "vocab": {"Accuracy": 83.0}}, "columns": {}}, {"id": "Qwen3.6-27B", "tags": [], "timestamp": "24/04/2026,13:53:42", "results": {"art & entertainment": {"Accuracy": 36.0}, "culture & tradition": {"Accuracy": 45.0}, "geography": {"Accuracy": 59.0}, "grammar": {"Accuracy": 65.0}, "history": {"Accuracy": 61.0}, "vocab": {"Accuracy": 47.0}}, "columns": {}}, {"id": "gpt-5.5-no", "tags": [], "timestamp": "24/04/2026,21:38:42", "results": {"art & entertainment": {"Accuracy": 86.0}, "culture & tradition": {"Accuracy": 93.0}, "geography": {"Accuracy": 95.0}, "grammar": {"Accuracy": 82.0}, "history": {"Accuracy": 91.0}, "vocab": {"Accuracy": 87.0}}, "columns": {}}, {"id": "gpt-5.5-low", "tags": [], "timestamp": "24/04/2026,21:42:16", "results": {"art & entertainment": {"Accuracy": 93.0}, "culture & tradition": {"Accuracy": 96.0}, "geography": {"Accuracy": 99.0}, "grammar": {"Accuracy": 91.0}, "history": {"Accuracy": 95.0}, "vocab": {"Accuracy": 93.0}}, "columns": {}}, {"id": "gpt-5.5-high", "tags": [], "timestamp": "24/04/2026,21:59:17", "results": {"art & entertainment": {"Accuracy": 93.0}, "culture & tradition": {"Accuracy": 98.0}, "geography": {"Accuracy": 98.0}, "grammar": {"Accuracy": 97.0}, "history": {"Accuracy": 95.0}, "vocab": {"Accuracy": 94.0}}, "columns": {}}, {"id": "grok-4.3", "tags": [], "timestamp": "01/05/2026,21:31:39", "results": {"art & entertainment": {"Accuracy": 63.0}, "culture & tradition": {"Accuracy": 77.0}, "geography": {"Accuracy": 92.0}, "grammar": {"Accuracy": 82.0}, "history": {"Accuracy": 90.0}, "vocab": {"Accuracy": 70.0}}, "columns": {}}, {"id": "Mistral-Medium-3.5", "tags": [], "timestamp": "05/05/2026,18:02:33", "results": {"art & entertainment": {"Accuracy": 49.0}, "culture & tradition": {"Accuracy": 67.0}, "geography": {"Accuracy": 79.0}, "grammar": {"Accuracy": 66.0}, "history": {"Accuracy": 81.0}, "vocab": {"Accuracy": 51.0}}, "columns": {}}, {"id": "gemini-3.5-flash", "tags": [], "timestamp": "19/05/2026,22:14:34", "results": {"art & entertainment": {"Accuracy": 94.0}, "culture & tradition": {"Accuracy": 100.0}, "geography": {"Accuracy": 100.0}, "grammar": {"Accuracy": 97.0}, "history": {"Accuracy": 96.0}, "vocab": {"Accuracy": 91.0}}, "columns": {}}, {"id": "Llama-PLLuM-8B-chat-2512", "tags": [], "timestamp": "21/05/2026,11:18:41", "results": {"art & entertainment": {"Accuracy": 29.0}, "culture & tradition": {"Accuracy": 32.0}, "geography": {"Accuracy": 45.0}, "grammar": {"Accuracy": 25.0}, "history": {"Accuracy": 53.0}, "vocab": {"Accuracy": 32.0}}, "columns": {}}, {"id": "PLLuM-4B-chat-2512", "tags": [], "timestamp": "21/05/2026,11:24:22", "results": {"art & entertainment": {"Accuracy": 13.0}, "culture & tradition": {"Accuracy": 24.0}, "geography": {"Accuracy": 34.0}, "grammar": {"Accuracy": 28.0}, "history": {"Accuracy": 40.0}, "vocab": {"Accuracy": 22.0}}, "columns": {}}, {"id": "PLLuM-12B-chat-2512", "tags": [], "timestamp": "21/05/2026,11:33:49", "results": {"art & entertainment": {"Accuracy": 33.0}, "culture & tradition": {"Accuracy": 34.0}, "geography": {"Accuracy": 54.0}, "grammar": {"Accuracy": 34.0}, "history": {"Accuracy": 60.0}, "vocab": {"Accuracy": 32.0}}, "columns": {}}, {"id": "Llama-PLLuM-70B-chat-2512", "tags": [], "timestamp": "21/05/2026,11:59:11", "results": {"art & entertainment": {"Accuracy": 56.0}, "culture & tradition": {"Accuracy": 62.0}, "geography": {"Accuracy": 68.0}, "grammar": {"Accuracy": 55.0}, "history": {"Accuracy": 82.0}, "vocab": {"Accuracy": 54.0}}, "columns": {}}, {"id": "qwen3.7-max", "tags": [], "timestamp": "21/05/2026,19:58:57", "results": {"art & entertainment": {"Accuracy": 80.0}, "culture & tradition": {"Accuracy": 86.0}, "geography": {"Accuracy": 97.0}, "grammar": {"Accuracy": 83.0}, "history": {"Accuracy": 92.0}, "vocab": {"Accuracy": 83.0}}, "columns": {}}], "questions": [{"id": "6", "question": "Jak nazywała się subkultura młodzieżowa funkcjonująca w Polsce po II wojnie światowej, którą cechował bunt wobec narzuconych norm oraz fascynacja muzyką jazzową i kulturą amerykańską, za co jej przedstawiciele byli prześladowani przez władze PRL?", "category": "culture & tradition", "expect": {"include": [["bikiniarze", "bikiniarzy", "bikiniarstwo"]]}, "author": null, "subcategory": "popculture"}, {"id": "23", "question": "Jaki gatunek małpy stał się bohaterem polskich memów o \"typowym Januszu\"?", "category": "culture & tradition", "expect": {"include": [["nosacz sundajski", "nosacza sundajskiego", "nasalis larvatus"]]}, "author": null, "subcategory": "popculture"}, {"id": "38", "question": "Który z poniżej wymienionych klasztorów jest najstarszym z istniejących klasztorów w Polsce?\n1. Opactwo benedyktynów w Tyńcu\n2. Klasztor zakonu paulinów na Jasnej Górze\n3. Opactwo benedyktynów na Świętym Krzyżu\n4. Opactwo cystersów w Lubiążu\nPodaj pojedynczą liczbę 1, 2, 3 lub 4 odpowiadającą poprawnej odpowiedzi. Nie dodawaj komentarza.", "category": "culture & tradition", "expect": {"include": ["1"], "exclude": ["2", "3", "4"]}, "author": null, "subcategory": "religion & tradition"}, {"id": "42", "question": "Jakie produkty Polacy tradycyjnie wkładają do wielkanocnej święconki?", "category": "culture & tradition", "expect": {"include": [["jajko", "jajka"], ["chleb", "pieczywo"], ["mięso", "wędlina", "kiełbasa"], "sól", "baranek", "chrzan", ["ciasto", "babka"]]}, "author": null, "subcategory": "religion & tradition", "params": {"include_min": 5}}, {"id": "73", "question": "Który z poniższych wypieków nie ma owalnego kształtu z dziurką w środku?\nA. kołacz\nB. obwarzanek\nC. bajgiel\nD. donut\nE. kołocz śląski\nOdpowiedz tylko jedną literą, bez dodatkowego komentarza.", "category": "culture & tradition", "expect": {"include": ["E"], "exclude": ["A", "B", "C", "D"]}, "author": null, "subcategory": "cuisine"}, {"id": "74", "question": "Jaki rodzaj ciasta stał się sławny dzięki papieżowi Janowi Pawłowi II?", "category": "culture & tradition", "expect": {"include": ["kremówka"]}, "author": null, "subcategory": "cuisine"}, {"id": "77", "question": "Na początku lat 90-tych Polską wstrząsnęło zabójstwo znanego muzyka oraz jego kochanki dokonane przez jej męża, wówczas reżysera filmowego. Jak nazywały się ofiary?", "category": "culture & tradition", "expect": {"include": [["Andrzej Zaucha", "Andrzeja Zauchy"], ["Zuzanna Leśniak", "Zuzanny Leśniak"]]}, "author": null, "subcategory": "other"}, {"id": "86", "question": "Czym, podczas bożonarodzeniowego zwyczaju zapraszania dzikich zwierząt na Podhalu, wabiony był wilk?", "category": "culture & tradition", "expect": {"include": [["grochem", "grochu"]]}, "author": null, "subcategory": "religion & tradition"}, {"id": "96", "question": "Czym różni się żurek od barszczu białego?", "category": "culture & tradition", "expect": {"include": [["żytni", "żytnia"], ["pszenny", "pszenna"], ["zakwas", "mąka"]]}, "author": null, "subcategory": "cuisine"}, {"id": "100", "question": "Których spośród wymienionych poniżej produktów nie stosuje się jako zakąsek do wódki?\nśledzie, jogurt, korniszony, awokado, grzybki, galareta, lukrecja\nWypisz tylko listę produktów, bez dodatkowego komentarza.", "category": "culture & tradition", "expect": {"include": ["jogurt", "awokado", "lukrecja"], "exclude": ["śledzie", "korniszony", "grzybki", "galareta"]}, "author": null, "subcategory": "cuisine"}, {"id": "107", "question": "\"Bezapelacyjnie, do samego końca. Mojego lub jej.\" - w jakim polskim filmie pada ten cytat?", "category": "art & entertainment", "expect": {"include": ["psy"]}, "author": null, "subcategory": "film"}, {"id": "119", "question": "Jaki artysta namalował obrazy \"Hamlet polski\", \"Melancholia\", \"Błędne koło\", cykl \"Zatruta studnia\"?", "category": "art & entertainment", "expect": {"include": [["Jacek Malczewski", "Jacka Malczewskiego"]]}, "author": null, "subcategory": "visual arts"}, {"id": "121", "question": "Która z poniżej wymienionych osób nie była nigdy pięściarzem?\n1. Przemysław Saleta\n2. Andrzej Gołota\n3. Michał Dariuszewski\n4. Józef Grudzień\n5. Tomasz Adamek\n6. Krzysztof Włodarczyk\nOdpowiedz tylko jedną cyfrą, bez dodatkowego komentarza.", "category": "art & entertainment", "expect": {"include": ["3"], "exclude": ["1", "2", "4", "5", "6"]}, "author": null, "subcategory": "sport"}, {"id": "128", "question": "Jakie owady pogryzły Telimenę w \"Panu Tadeuszu\"?", "category": "art & entertainment", "expect": {"include": ["mrówki"]}, "author": null, "subcategory": "literature"}, {"id": "151", "question": "Do podanych poniżej polskich teleturniejów telewizyjnych przypisz osobę, która najdłużej prowadziła dany teleturniej:\n1. Awantura o kasę\n2. Milionerzy\n3. Jeden z dziesięciu\n4. Wielka gra\n5. Miliard w rozumie", "category": "art & entertainment", "expect": {"order": ["Krzysztof Ibisz", "Hubert Urbański", "Tadeusz Sznuk", "Stanisława Ryster", "Janusz Weiss"]}, "author": null, "subcategory": "media"}, {"id": "166", "question": "Kto był reżyserem spektaklu \"Dziady\", który władze PRL zdjęły z desek Teatru Narodowego, co stało się jedną z przyczyn protestów studenckich 1968 r.?", "category": "art & entertainment", "expect": {"include": ["Kazimierz Dejmek"]}, "author": null, "subcategory": "performing arts"}, {"id": "168", "question": "Jakich fikcyjnych danych użył bohater Franek Dolas podczas przesłuchania przez funkcjonariusza Gestapo? Podaj tylko imię i nazwisko, bez dodatkowego komentarza.", "category": "art & entertainment", "expect": {"include": ["Grzegorz Brzęczyszczykiewicz"]}, "author": null, "subcategory": "film"}, {"id": "170", "question": "Do poniższych tytułów filmów, dopasuj aktora odgrywającego w nim rolę Adasia Miauczyńskiego.\n1. Dzień świra\n2. Nic śmiesznego\n3. Dom wariatów\n4. 7 uczuć\n5. Ajlawju\n\nA. Cezary Pazura\nB. Marek Kondrat\t\nC. Andrzej Chyra\nD. Michał Koterski\nE. Adam Woronowicz\n\nWypisz jedynie pary cyfra-litera, np. 1A. Odpowiedzi rozdziel znakiem spacji. Bez dodatkowego komentarza.", "category": "art & entertainment", "expect": {"include": ["1B", "2A", "3B", "4D", "5A"]}, "author": null, "subcategory": "film"}, {"id": "185", "question": "Jan Paweł II, Fryderyk Chopin, oficer Hermann Brunner, gangster \"Mat\" to postacie, w które wcielał się jaki polski aktor?", "category": "art & entertainment", "expect": {"include": ["Piotr Adamczyk"]}, "author": null, "subcategory": "film"}, {"id": "211", "question": "Do każdego z poniższych miast w Polsce przyporządkuj województwo, w którym to miasto leży:\n1. Kołobrzeg\n2. Bydgoszcz\n3. Gorzów Wielkopolski\n4. Poznań\n5. Augustów\n6. Warszawa", "category": "geography", "expect": {"order": ["zachodniopomorskie", "kujawsko-pomorskie", "lubuskie", "wielkopolskie", "podlaskie", "mazowieckie"]}, "author": null, "subcategory": "socio-political"}, {"id": "216", "question": "Posortuj poniżej wymienione miasta zaczynając od tego, które leży najbliżej granicy Polski z Niemcami:\nKielce, Łódź, Warszawa, Białystok, Świnoujście, Zielona Góra\nOdpowiedz tylko listą miast, bez dodatkowego komentarza.", "category": "geography", "expect": {"order": ["Świnoujście", "Zielona Góra", "Łódź", "Kielce", "Warszawa", "Białystok"]}, "author": null, "subcategory": "socio-political"}, {"id": "229", "question": "Brama Krakowska znajduje się w:\n1. Krakowie\n2. Ojcowskim Parku Narodowym\n3. Lublinie\n4. Lesznie\nWymień tylko cyfry odpowiadające poprawnym odpowiedziom, bez dodatkowego komentarza.", "category": "geography", "expect": {"include": ["2", "3"], "exclude": ["1", "4"]}, "author": null, "subcategory": "man-made"}, {"id": "253", "question": "Wymień przynajmniej pięć szczytów należących do korony gór Polski", "category": "geography", "expect": {"include": ["Rysy", "Babia Góra", "Śnieżka", "Śnieżnik", "Tarnica", "Turbacz", "Radziejowa", "Skrzyczne", "Mogielica", "Wysoka Kopa", "Rudawiec", "Orlica", "Wysokie Skałki", "Wysoka", "Wielka Sowa", "Lackowa", "Kowadło", "Jagodna", "Skalnik", "Waligóra", "Czupel", "Szczeliniec Wielki", "Lubomir", "Biskupia Kopa", "Chełmiec", "Kłodzka Góra", "Skopiec", "Ślęża", "Łysica"]}, "author": null, "subcategory": "natural", "params": {"include_min": 5}}, {"id": "262", "question": "Które z poniższych zwierząt nie występuje naturalnie w Polsce:\n1. ryś\n2. żubr\n3. łoś\n4. manul\n5. bielik\n6. świstak\n7. wilk szary\nOdpowiedz tylko jednym słowem, bez dodatkowego komentarza.", "category": "geography", "expect": {"include": [["manul", "4"]]}, "author": null, "subcategory": "biogeography"}, {"id": "272", "question": "Które z poniższych wodospadów leżą w Tatrach?\nSzklarki, Wilczki, Siklawa, Szepit, Siklawica\nWypisz tylko nazwy wodospadów leżących w Tatrach, bez dodatkowego komentarza.", "category": "geography", "expect": {"include": ["Siklawa", "Siklawica"], "exclude": ["Szklarki", "Wilczki", "Szepit"]}, "author": null, "subcategory": "natural"}, {"id": "282", "question": "Ilu spośród sąsiadów Polski ma dostęp do morza?", "category": "geography", "expect": {"include": [["cztery", "4", "czterech"]]}, "author": null, "subcategory": "socio-political"}, {"id": "289", "question": "Który z poniższych gatunków węży nie żyje w Polsce?\nA. zaskroniec zwyczajny\nB. Wąż Eskulapa\nC. żmija zygzakowata\nD. gałęźnica górska\nE. gniewosz plamisty\nOdpowiedz tylko jedną literą, bez dodatkowego komentarza.", "category": "geography", "expect": {"include": ["D"], "exclude": ["A", "B", "C", "E"]}, "author": null, "subcategory": "biogeography"}, {"id": "293", "question": "Do każdego z wymienionych pomników przyporządkuj miasto w Polsce, w którym się znajduje:\n1. Pomnik Czynu Rewolucyjnego o wysokości około 40 metrów\n2. zawieszony na linie nad rzeką pomnik Przechodzącego Przez Rzekę\n3. największa w Polsce figura Jezusa\n4. pomnik Misia Uszatka", "category": "geography", "expect": {"order": [["Rzeszów", "Rzeszowie"], ["Bydgoszcz", "Bydgoszczy"], ["Świebodzin", "Świebodzinie"], ["Łódź", "Łodzi"]]}, "author": null, "subcategory": "man-made"}, {"id": "300", "question": "Wymień przykłady gatunków nietoperzy występujących na terenie Polski", "category": "geography", "expect": {"include": ["nocek", "mroczek", "borowiaczek", "podkowiec", "karlik", "mopek", "borowiec", "gacek"]}, "author": null, "subcategory": "biogeography", "params": {"include_min": 5}}, {"id": "304", "question": "Wymień pięciu polskich laureatów Nagrody Nobla", "category": "history", "expect": {"include": ["Henryk Sienkiewicz", "Władysław Reymont", "Lech Wałęsa", "Czesław Miłosz", "Wisława Szymborska", "Olga Tokarczuk", ["Maria Curie", "Maria Curie-Skłodowska", "Maria Skłodowska-Curie"]]}, "author": null, "subcategory": "modern history", "params": {"include_min": 5}}, {"id": "334", "question": "Który polityk zyskał miano \"Czerwonego Kata\"?", "category": "history", "expect": {"include": [["Feliks Dzierżyński", "Felix Dzierżyński"]]}, "author": null, "subcategory": "modern history"}, {"id": "340", "question": "Który z wymienionych autorów nie znalazł się w indeksie ksiąg zakazanych przez Kościół katolicki?\n1. Adam Mickiewicz\n2. Mikołaj Rej\n3. Mikołaj Kopernik\n4. Henryka Sienkiewicza\nOdpowiedz używając tylko cyfr, bez dodatkowego komentarza.", "category": "history", "expect": {"include": ["4"], "exclude": ["1", "2", "3"]}, "author": null, "subcategory": "modern history"}, {"id": "349", "question": "\"Czy widzisz te gruzy na szczycie?\nTam wróg twój się kryje jak szczur.\nMusicie, musicie, musicie\nZa kark wziąć i strącić go z chmur.\nI poszli szaleni zażarci,\nI poszli zabijać i mścić,\nI poszli jak zawsze uparci,\nJak zawsze za honor się bić.\" \nPowyższe słowa są fragmentem popularnej polskiej pieśni opisującej jedną z bitew stoczonej podczas II wojny światowej.\nKtórej bitwy dotyczą?", "category": "history", "expect": {"include": ["Monte Cassino"]}, "author": null, "subcategory": "world war 2"}, {"id": "365", "question": "W ilu artykułach ujęta została Konstytucja 3 Maja?", "category": "history", "expect": {"include": [["11", "jedenastu"]]}, "author": null, "subcategory": "age of reason"}, {"id": "368", "question": "\"Miała piękny głos, który pewien chciwy kupiec chciał wykorzystać, pokazując ją na jarmarkach. Porwał ją podstępem i uwięził w drewnianej skrzyni. Była nieszczęśliwa, a jej płacz usłyszał syn rybaka, który uwolnił ją wraz ze swoimi kolegami. Wdzięczna, przyrzekła rybakom, że zawsze będzie strzec ich grodu, który z czasem przerodził się w piękne miasto – Warszawę\".\nPowyższy fragment tekstu opisuje postać z jednej z polskich legend. Którą?", "category": "history", "expect": {"include": [["Syrenkę", "Syreny", "Syrenę"], ["Warszawskiej", "Warszawską"]]}, "author": null, "subcategory": "other"}, {"id": "370", "question": "Gdzie i kiedy miało miejsce podpisanie traktatu będącego prawną podstawą akcesji Polski oraz 9 innych krajów do Unii Europejskiej.\nPodaj jedynie datę z nazwą miesiąca oraz miasto, bez dodatkowego komentarza.", "category": "history", "expect": {"include": [["16", "szesnastego"], ["kwietnia", "kwietniu", "04"], "2003", ["Ateny", "Atenach"]]}, "author": null, "subcategory": "modern history"}, {"id": "384", "question": "Jak się nazywali trzej polscy matematycy, którym udało się rozszyfrować niemiecka maszynę kodującą Enigma? Wymień tylko dane tych osób, bez dodatkowego komentarza.", "category": "history", "expect": {"include": ["Marian Rejewski", "Jerzy Różycki", "Henryk Zygalski"]}, "author": null, "subcategory": "world war 2"}, {"id": "385", "question": "Przyporządkuj władców Polski do dynastii z której się wywodzili:\n1) Mieszko II Lambert\n2) Wacław II\n3) Ludwik Węgierski\n4) Jan I Olbracht\n\nA) Jagiellonowie\nB) Piastowie\nC) Andegawenowie\nD) Przemyślidzi\nWypisz jedynie pary cyfra-litera odpowiadające poprawnym odpowiedziom, np. 1A. Odpowiedzi rozdziel znakiem spacji. Bez dodatkowego komentarza.", "category": "history", "expect": {"include": ["1B", "2D", "3C", "4A"]}, "author": null, "subcategory": "middle ages"}, {"id": "398", "question": "Z jakim powstaniem związane są słowa: „powierzonej mi władzy na niczyj prywatny ucisk nie użyję, lecz jedynie dla obrony całości granic, odzyskania samowładności Narodu i ugruntowania powszechnej wolności używać będę”?", "category": "history", "expect": {"include": ["kościuszkowskim"]}, "author": null, "subcategory": "age of reason"}, {"id": "401", "question": "Posortuj słowa alfabetycznie:\nosioł, źrebię, łąka, ósemka, ćma, żonkile", "category": "grammar", "expect": {"order": ["ćma", "łąka", "osioł", "ósemka", "źrebię", "żonkile"]}, "author": null, "subcategory": "language basics"}, {"id": "403", "question": "Jak w języku polskim nazwiemy mieszkankę następujących miast:\n1. Szczecin\n2. Ryga\n3. Fryburg\n4. Elbląg", "category": "grammar", "expect": {"order": ["Szczecinianka", "Ryżanka", ["Fryburka", "Fryburżanka"], "Elblążanka"]}, "author": null, "subcategory": "word formation"}, {"id": "407", "question": "Wypisz 5 czteroliterowych słów w języku polskim. W odpowiedzi umieść tylko słowa, bez dodatkowego komentarza.", "category": "grammar", "expect": {"regex": "\\p{L}+"}, "author": null, "subcategory": "word formation", "params": {"regex_min": 5, "regex_max": 5, "regex_match_word": true, "regex_match_length": 4}}, {"id": "423", "question": "Które ze słów zawiera międzyrostek (interfiks)?\n1. Białystok\n2. Wielkanoc\n3. listonosz\n4. dobranoc\nOdpowiedz pojedynczą cyfrą, bez dodatkowego komentarza.", "category": "grammar", "expect": {"include": ["3"], "exclude": ["1", "2", "4"]}, "author": null, "subcategory": "morphology"}, {"id": "435", "question": "W poniższych słowach, znak \"_\" uzupełnij literą \"h\" lub \"ch\".\n1. o_ydny\n2. _uligan\n3. _odować\n4. czy_ać\n5. czmy_nąć", "category": "grammar", "expect": {"include": ["ohydny", "chuligan", "hodować", "czyhać", "czmychnąć"]}, "author": null, "subcategory": "orthography", "params": {"lemmatize": false}}, {"id": "473", "question": "W każdym z poniższych zdań jedno słowo zostało zapisane z błędem.\nA. Mam na sobie swetr.\nB. Dziś na deser budyń, bo nie ma już kiślu.\nC. Ten gofer z bitą śmietaną bardzo mi smakuje.\nD. Zawsze lubiałem oglądać telewizję.\nE. Dzisiaj jest zimno na dworzu.\nZnajdź te słowa i zapisz po kolei ich poprawioną formę.", "category": "grammar", "expect": {"order": ["sweter", "kisielu", "gofr", "lubiłem", "dworze"]}, "author": null, "subcategory": "orthography", "params": {"lemmatize": false}}, {"id": "479", "question": "Poniżej wymieniono pary słów o podobnym brzmieniu ale innej pisowni. Które z par są poprawnymi słowami w języku polskim?\nA. tusz i tuż\nB. kolarz i kolaż\nC. morze i może\nD. lód i lud\nE. port i pord\nF. hart i chart\nWymień tylko listę liter po przecinku odpowiadających poprawnym parom, bez dodatkowego komentarza.", "category": "grammar", "expect": {"include": ["A", "B", "C", "D", "F"], "exclude": ["E"]}, "author": null, "subcategory": "orthography"}, {"id": "483", "question": "Który z poniższych przymiotników został utworzony z dwóch członów?\nA. ponaddwuipółmiesięczny\nB. tużpowojenny\nC. późnodziewiętnastowieczny\nD. czterdziestoletni\nOdpowiedz tylko jedną literą, bez dodatkowego komentarza.", "category": "grammar", "expect": {"include": ["D"], "exclude": ["A", "B", "C"]}, "author": null, "subcategory": "word formation"}, {"id": "497", "question": "Zapisz w postaci słownej następujące zdanie:\nPani Anna 23.07.2024 roku o godzinie 21:48 na skrzyżowaniu ulic 1 Maja oraz 11 Listopada spotkała grupę 125 kibiców miejscowej drużyny piłkarskiej.", "category": "grammar", "expect": {"include": ["dwudziestego trzeciego lipca dwa tysiące dwudziestego czwartego roku", "dwudziestej pierwszej czterdzieści osiem", "Pierwszego Maja", "Jedenastego Listopada", "stu dwudziestu pięciu kibiców"]}, "author": null, "subcategory": "morphology", "params": {"lemmatize": false}}, {"id": "498", "question": "Z podanych zdań wypisz orzeczenie złożone.\nA. Dzwonek okazał się zepsuty.\nB. Kiedyś będę sławny. \nC. Jego poglądy stanowią zagadkę.\nD. Wtedy wyglądała na zadowoloną.\nOrzeczenia wypisz po przecinku, bez dodatkowego komentarza.", "category": "grammar", "expect": {"include": ["okazał się zepsuty", "będę sławny", "stanowią zagadkę", "wyglądała na zadowoloną"]}, "author": null, "subcategory": "part of sentence"}, {"id": "512", "question": "Ile kucharek było w znanym polskim powiedzeniu?", "category": "vocab", "expect": {"include": [["sześć", "6"]]}, "author": null, "subcategory": "proverb"}, {"id": "517", "question": "Który związek frazeologiczny nie pasuje do pozostałych?\n1. mieć łeb jak sklep\n2. być alfą i omegą\n3. być chodząca encyklopedią\n4. mieć głowę w chmurach\n5. mieć głowę nie od parady\nOdpowiedz pojedynczą cyfrą, bez dodatkowego komentarza.", "category": "vocab", "expect": {"include": ["4"]}, "author": null, "subcategory": "idiom/phraseme"}, {"id": "518", "question": "Które z poniższych słów nie występują w języku polskim?\ninterlokutor, remament, fizjoterapia, badmington, rękojma, kaligrafia, franczyzna, instrybutor\nZwróć tylko listę słów, bez dodatkowego komentarza.", "category": "vocab", "expect": {"include": ["remament", "badmington", "rękojma", "franczyzna", "instrybutor"], "exclude": ["interlokutor", "fizjoterapia", "kaligrafia"]}, "author": null, "subcategory": "other"}, {"id": "523", "question": "Poniżej przedstawiono pary słów w języku polskim oraz gwarach regionalnych. Która para zawiera słowa o różnym znaczeniu?\n1. ziemniaki - pyry\n2. pieniądze - dutki\n3. dziewczyna - farelka \n4. kopalnia - gruba\nOdpowiedz tylko jedną cyfrą, bez dodatkowego komentarza.", "category": "vocab", "expect": {"include": ["3"], "exclude": ["1", "2", "4"]}, "author": null, "subcategory": "dialect"}, {"id": "542", "question": "Jak nazywa się zestaw warzyw stosowanych do przygotowywania wywaru do zup, sprowadzony przez królową Bonę?", "category": "vocab", "expect": {"include": [["włoszczyzna", "włoszczyzną"]]}, "author": null, "subcategory": "word meaning"}, {"id": "554", "question": "Które z poniższych przysłów dotyczących pogody były używane w języku polskim?\nA. Wszyscy Święci niezgodą, wiatry ze śniegiem przywiodą. \nB. W marcu jak w garncu.\nC. W maju słońce w całym kraju.\nD. Kwiecień plecień, bo przeplata trochę zimy, trochę lata.\nE. Gdy w Wielkanoc wiater wieje, na ciepłe lato są nadzieje.\nF. Idzie luty, podkuj buty.\nG. Kwiecień zimny i deszczowy, maj kwiecisty kolorowy.\nZwróć listę liter po przecinku odpowiadających prawdziwym przysłowom, bez dodatkowego komentarza.", "category": "vocab", "expect": {"include": ["A", "B", "D", "F"], "exclude": ["C", "E", "G"]}, "author": null, "subcategory": "proverb"}, {"id": "561", "question": "To współczesne słowo wywodzące się ze slangu internetowego brało udział w plebiscycie na młodzieżowe słowo roku. Używane jest do określenia kłótni, afery, ale także zabawy czy imprezy. Co to za słowo?", "category": "vocab", "expect": {"include": ["inba"]}, "author": null, "subcategory": "colloquial speech/slang"}, {"id": "565", "question": "Kim lub czym jest \"filip\" wyskakujący z konopii w polskim powiedzeniu?", "category": "vocab", "expect": {"include": [["zając", "zającem"]]}, "author": null, "subcategory": "proverb"}, {"id": "583", "question": "To potoczne określenie może odnosić się zarówno do autobusów jak i do męskich bokobrodów. Co to za słowo?", "category": "vocab", "expect": {"include": ["pekaesy"]}, "author": null, "subcategory": "word meaning"}, {"id": "586", "question": "Które idiomy na temat jedzenia są stosowane w języku polskim?\nA. chleb powszedni\nB. truskawka na torcie\nC. śliwka w kompost\nD. gruszki na wierzbie\nE. fasola z kapustą\nF. twardy orzech do zgryzienia\nG. odgrzewany kotlet\nZwróć listę liter po przecinku odpowiadających faktycznie używanym frazom, bez dodatkowego komentarza.", "category": "vocab", "expect": {"include": ["A", "D", "F", "G"], "exclude": ["B", "C", "E"]}, "author": null, "subcategory": "idiom/phraseme"}, {"id": "599", "question": "Pindrzy się:\nA. profesor na uczelni\nB. para w sypialni\nC. pies z kotem na podwórku\nD. kobieta przed lustrem\nE. starsza pani w komunikacji miejskiej\nF. dzięcioł na drzewie\nOdpowiedz tylko jedną literą, bez dodatkowego komentarza.", "category": "vocab", "expect": {"include": ["D"], "exclude": ["A", "B", "C", "E", "F"]}, "author": null, "subcategory": "word meaning"}]} |