List your company

Code Generation on MLGym-Bench

75Pass@3MTL (I)
57.63262.14166.6571.159Apr 15, 2026

Evaluation results

MethodLinks
MTL (I)Model=GPT-5-mini, Method=MTL (I)2026.0475
Zero-shotModel=GPT-5-mini, Method=Zero-shot2026.0466.7
MTL (S)Model=GPT-5-mini, Method=MTL (S)2026.0466.7
MTL (I)Model=DeepSeek V3.2, Method=MTL (I)2026.0466.7
MTL (T)Model=GPT-5-mini, Method=MTL (T)2026.0458.3
MTL (W)Model=GPT-5-mini, Method=MTL (W)2026.0458.3
Zero-shotModel=DeepSeek V3.2, Method=Zero-shot2026.0458.3
Zero-shotModel=Qwen3-Coder-480B-A35B-Instruct, Method=Zero-shot2026.0458.3
MTL (I)Model=Qwen3-Coder-480B-A35B-Instruct, Method=MTL (I)2026.0458.3