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

Reasoning on GPQA-D

59.47Accuracy

T3S

0.221215.603130.98546.3669Jun 30, 2025Aug 21, 2025Oct 12, 2025Dec 4, 2025Jan 25, 2026Mar 18, 2026May 10, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.01
59.47
2026.01
58.59
2026.01
58.59
2026.01
58.33
2026.01
58.33
2026.01
58.21
2026.01
57.77
2026.01
57.32
2026.01
56.34
2025.06
49.6
2025.06
48.6
2025.12
46.5
2025.12
42.9
2025.12
42.9
2025.12
40.5
2025.12
40.4
2025.06
40.1
2025.12
39.9
2026.05
39.9
2025.12
39.4
2025.12
39.4
2026.05
38.8
2026.05
38.4
2026.05
36.9
2025.12
36.8
2025.12
36.4
2026.05
36.4
2025.12
35.4
2026.05
35.4
2025.12
35.3
2025.12
33.3
2026.05
32.8
2026.05
32.3
2026.05
31.3
2026.05
31.3
2025.06
30.6
2026.05
26.8
2025.12
26.3
2026.05
26.3
2026.05
24.8
2026.05
23.2
2026.05
22.7
2026.05
21.7
2026.05
19.2
2026.02
17.08
2026.02
15.05
2026.02
13.79
2026.02
13.73
2026.02
13.47
2026.02
12.99
2026.05
7.1
2026.05
5.6
2026.05
2.5