{"benchmark_id":"theoremqa","name":"TheoremQA","parent_benchmark":null,"categories":["math","physics","reasoning","finance"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"A theorem-driven question answering dataset containing 800 high-quality questions covering 350+ theorems from Math, Physics, EE&CS, and Finance. Designed to evaluate AI models' capabilities to apply theorems to solve challenging university-level science problems.","paper_link":"https://arxiv.org/abs/2305.12524","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.529376+00:00","updated_at":"2026-07-05T18:28:03.470534+00:00","statistics":{"total_models":6,"average_score":0.3898333333333334,"min_score":0.253,"max_score":0.444,"score_stddev":0.07754590038594349,"verified_count":0,"self_reported_count":6},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen2-72b-instruct","model_name":"Qwen2 72B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.444,"normalized_score":0.444,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2-72B","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-23","param_count":72000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"qwen-2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.441,"normalized_score":0.441,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"TheoremQA benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":32500000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"qwen-2.5-coder-32b-instruct","model_name":"Qwen2.5-Coder 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.431,"normalized_score":0.431,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/abs/2409.12186","analysis_method":"accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":32000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"qwen-2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.43,"normalized_score":0.43,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"TheoremQA benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":14700000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"qwen-2.5-coder-7b-instruct","model_name":"Qwen2.5-Coder 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.34,"normalized_score":0.34,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/abs/2409.12186","analysis_method":"accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":7000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"qwen2-7b-instruct","model_name":"Qwen2 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.253,"normalized_score":0.253,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2-7B-Instruct","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-23","param_count":7620000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}