List your company

General Reasoning on GPQA (GPQA Metric)

35.04GPQA AccuracyINSIGHT
25.99228.34130.6933.039Mar 2, 2026

Evaluation results

MethodLinks
INSIGHTModel=Qwen3-4B2026.0335.04
RANDOMModel=Qwen3-4B2026.0334.38
EXPECTED-DIFFICULTYModel=Qwen3-4B2026.0333.5
INVERSE-EVIDENCEModel=Qwen3-4B2026.0333.48
MOPPSModel=Qwen3-4B2026.0333.26
INSIGHTModel=Qwen3-1.7B2026.0330.36
RANDOMModel=Qwen3-1.7B2026.0330.2
MOPPSModel=Qwen3-1.7B2026.0330.1
INVERSE-EVIDENCEModel=Qwen3-1.7B2026.0329.69
INSIGHTModel=Qwen3-0.6B2026.0329.5
INVERSE-EVIDENCEModel=Qwen3-0.6B2026.0329.46
MOPPSModel=Qwen3-0.6B2026.0327.9
RANDOMModel=Qwen3-0.6B2026.0326.34