Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Science Reasoning on GPQA 5-shot

33.3Accuracy

Baseline

28.82829.98931.1532.311May 9, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
33.30.52561
2026.05
32.611.6824.8
2026.05
32.422462
2026.05
32.112.11713.3
2026.05
32.122.3549.6
2026.05
31.98.3289.1
2026.05
30.642561
2026.05
30.67.6620.7
2026.05
2910.11242.1