| benchmark,group,selected_score,evaluator_path,evaluator_sha256_12 |
| Math Reasoning,Core Reasoning Tasks,0.584,evaluation/benchmarks/math_reasoning/eval.py,e8fedcb45db0 |
| Logical Reasoning,Core Reasoning Tasks,0.821,evaluation/benchmarks/logical_reasoning/eval.py,28bbb5a467cc |
| Common Sense,Core Reasoning Tasks,0.752,evaluation/benchmarks/common_sense/eval.py,fe6abc34fdd8 |
| Reading Comprehension,Language Understanding,0.719,evaluation/benchmarks/reading_comprehension/eval.py,97e2e7135134 |
| Question Answering,Language Understanding,0.636,evaluation/benchmarks/question_answering/eval.py,adcf2ed2e8d3 |
| Text Classification,Language Understanding,0.844,evaluation/benchmarks/text_classification/eval.py,1903d3adf96a |
| Sentiment Analysis,Language Understanding,0.815,evaluation/benchmarks/sentiment_analysis/eval.py,cde0649cba98 |
| Code Generation,Generation Tasks,0.669,evaluation/benchmarks/code_generation/eval.py,54fe6c62e389 |
| Creative Writing,Generation Tasks,0.631,evaluation/benchmarks/creative_writing/eval.py,9fff108de207 |
| Dialogue Generation,Generation Tasks,0.661,evaluation/benchmarks/dialogue_generation/eval.py,63972646b638 |
| Summarization,Generation Tasks,0.783,evaluation/benchmarks/summarization/eval.py,fb1790e2b432 |
| Translation,Specialized Capabilities,0.824,evaluation/benchmarks/translation/eval.py,9447fa9aaf83 |
| Knowledge Retrieval,Specialized Capabilities,0.691,evaluation/benchmarks/knowledge_retrieval/eval.py,80e08edad832 |
| Instruction Following,Specialized Capabilities,0.778,evaluation/benchmarks/instruction_following/eval.py,435cdef3f8af |
| Safety Evaluation,Specialized Capabilities,0.804,evaluation/benchmarks/safety_evaluation/eval.py,447544f7e183 |
|
|
