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

Reasoning on SuperGPQA (Pass@1, Pass@4)

38.4Pass@1

CER

20.30425.00229.734.398Sep 18, 2025Oct 17, 2025Nov 15, 2025Dec 14, 2025Jan 12, 2026Feb 10, 2026Mar 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
38.4-
2026.03
38.3-
2026.03
37.7-
2026.03
37.7-
2026.03
36.2-
2026.03
35.5-
2026.03
35.2-
2026.03
35.2-
2026.03
34.2-
2026.03
33.5-
2026.03
32.6-
2025.09
30.257
2025.09
29.753.3
2026.03
29.1-
2026.03
27-
2025.09
26.554.1
2026.03
21-