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

Scientific Reasoning on GPQA Diamond (Accuracy, Avg.)

74.24Accuracy

MILES

-1.00418.530538.06557.5995May 27, 2026Jun 3, 2026Jun 10, 2026Jun 17, 2026Jun 24, 2026Jul 1, 2026Jul 8, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.07
74.24-
2026.07
73.74-
2026.07
73.23-
2026.07
72.23-
2026.07
71.72-
2026.07
71.72-
2026.07
70.71-
2026.07
70.2-
2026.07
70.2-
2026.07
68.94-
2026.07
68.69-
2026.07
68.18-
2026.07
67.68-
2026.07
66.67-
2026.07
64.65-
2026.07
63.64-
2026.07
61.62-
2026.07
61.11-
2026.07
59-
2026.07
59-
2026.07
58-
2026.07
57-
2026.07
57-
2026.07
56-
2026.07
55-
2026.07
55-
2026.07
54-
2026.07
54-
2026.07
54-
2026.07
52-
2026.06
51.45-
2026.06
50.54-
2026.06
50.19-
2026.06
49.72-
2026.06
49.4-
2026.06
49.15-
2026.06
49.02-
2026.06
49.02-
2026.07
49-
2026.06
47.57-
2026.06
44.48-
2026.07
42.42-
2026.06
38.38-
2026.06
37.88-
2026.06
37.37-
2026.07
37.37-
2026.06
36.87-
2026.05
36.467.83
2026.06
36.36-
2026.06
35.92-
2026.06
35.86-
2026.05
35.3561.85
2026.06
35.23-
2026.06
35.23-
2026.06
35.01-
2026.06
34.5-
2026.06
34.44-
2026.06
33.84-
2026.06
33.62-
2026.06
33.14-
2026.05
32.852.2
2026.06
32.8-
2026.05
32.156.11
2026.05
31.8251.1
2026.05
31.3151.13
2026.06
30.93-
2026.05
30.8155.8
2026.05
30.852.32
2026.06
28.78-
2026.05
28.2853.39
2026.06
28.28-
2026.06
27.78-
2026.06
27.78-
2026.05
27.2762.42
2026.05
27.2750.27
2026.06
27.27-
2026.06
27.27-
2026.05
26.6448.93
2026.06
26.26-
2026.05
24.7547.26
2026.06
24.24-
2026.06
23.74-
2026.06
23.23-
2026.06
23.23-
2026.06
22.22-
2026.06
22.22-
2026.06
21.72-
2026.05
20.7138.19
2026.05
9.4746.63
2026.05
8.8438.52
2026.05
8.2145.72
2026.05
3.6645.63
2026.05
3.4146.49
2026.05
1.8934.73
2026.06
-95.5
2026.06
-95.5
-92
2026.06
-94.3
2026.06
-93.6
2026.06
-59.6
Showing 100 of 103 rows