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

General Reasoning on GPQA Diamond (ACC, A.Tok, epsilon^3)

72.6Accuracy

QwenLong L1.5-30B

24.936837.310949.68562.0591May 10, 2026May 11, 2026May 13, 2026May 14, 2026May 16, 2026May 17, 2026May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
72.6--
2026.05
72.3--
2026.05
70.1--
2026.05
67.7--
2026.05
65.4--
2026.05
48.987,124.4434
2026.05
38.883,892.6239
2026.05
36.892,915.7947
2026.05
36.866,471.2621
2026.05
36.864,060.4333
2026.05
34.854,763.0425
2026.05
33.833,603.6632
2026.05
32.827,465.2214
2026.05
30.86,695.5714
2026.05
30.86,237.9815
2026.05
29.797,419.912
2026.05
28.75,106.916
2026.05
26.776,140.9812
2026.05
26.775,768.0812