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

Scientific Question Answering on GPQA (Score)

33.48Score

LARFT

23.96426.434528.90531.3755Feb 25, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.02
33.48
2026.02
33.26
2026.02
33.04
2026.02
32.81
2026.02
32.59
2026.02
32.37
2026.02
32.14
2026.02
32.14
2026.02
32.14
2026.02
31.7
2026.02
31.47
2026.02
31.25
2026.02
31.25
2026.02
31.25
2026.02
31.03
2026.02
30.58
2026.02
30.13
2026.02
29.91
2026.02
29.46
2026.02
29.24
2026.02
29.01
2026.02
28.35
2026.02
28.35
2026.02
27.9
2026.02
25.45
2026.02
24.33
2026.02
24.33
2026.02
24.33