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

Foundation Model Evaluation on AGIEval

58.1Accuracy

RLVR

17.85228.30138.7549.199Jul 2, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.07
58.10.53437.7
2026.07
58.10.68219.7
2026.07
57.80.68815.4
2026.07
57.50.66420.5
2026.07
53.70.71120.8
2026.07
510.54337.5
2026.07
50.80.74514.7
2026.07
49.10.75310.5
2026.07
37.30.52246.8
2026.07
37.30.6624.6
2026.07
37.20.65221.8
2026.07
34.80.55742.3
2026.07
34.40.65811.1
2026.07
32.10.59424
2026.07
28.60.64435.2
2026.07
19.40.6117.2