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

Scientific Question Answering on GPQA D (Accuracy (mean@4, %) & Speedup)

38.5Accuracy (mean@4)

GRPO

19.7824.6429.534.36May 8, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
38.51
2026.05
38.31.43
2026.05
38.12.38
2026.05
37.40.63
2026.05
36.80.75
2026.05
34.51.19
2026.05
29.10.81
2026.05
29.12.51
2026.05
291.62
2026.05
28.8-
2026.05
27.80.95
2026.05
27.41
2026.05
26.71.3
2026.05
25.41
2026.05
25.31.13
2026.05
25.31.26
2026.05
24.90.95
2026.05
24.50.82
2026.05
23.22.04
2026.05
22.2-
2026.05
20.5-