List your company

Engineering Reasoning on MMLU-Pro Engineering

81AccuracyMILES
39.9250.58561.2571.915Jul 8, 2026

Evaluation results

MethodLinks
MILESBackbone=Qwen3-30B-Instruct, Inference Strategy=MILES2026.0781
MILESBackbone=GPT-4.1, Inference Strategy=MILES2026.0780
SCBackbone=GPT-4.1, Inference Strategy=SC2026.0778.5
SCBackbone=Qwen3-30B-Instruct, Inference Strategy=SC2026.0778
ZS-CoTBackbone=GPT-4.1, Inference Strategy=ZS-CoT2026.0775.5
BoTBackbone=Qwen3-30B-Instruct, Inference Strategy=BoT2026.0775.5
MILESBackbone=GPT-4.1-mini, Inference Strategy=MILES2026.0775
ZS-CoTBackbone=Qwen3-30B-Instruct, Inference Strategy=ZS-CoT2026.0774.5
SCBackbone=GPT-4.1-mini, Inference Strategy=SC2026.0773.5
DCBackbone=GPT-4.1, Inference Strategy=DC2026.0772
MILESBackbone=GPT-OSS-20B, Inference Strategy=MILES2026.0771
BoTBackbone=GPT-4.1-mini, Inference Strategy=BoT2026.0770.5
SCBackbone=GPT-OSS-20B, Inference Strategy=SC2026.0770
ZS-CoTBackbone=GPT-OSS-20B, Inference Strategy=ZS-CoT2026.0768.5
DCBackbone=GPT-4.1-mini, Inference Strategy=DC2026.0767.5
BoTBackbone=GPT-4.1, Inference Strategy=BoT2026.0767.5
DCBackbone=GPT-OSS-20B, Inference Strategy=DC2026.0766.5
ZS-CoTBackbone=GPT-4.1-mini, Inference Strategy=ZS-CoT2026.0765.5
DCBackbone=Qwen3-30B-Instruct, Inference Strategy=DC2026.0752
BoTBackbone=GPT-OSS-20B, Inference Strategy=BoT2026.0741.5