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

Reasoning on MMLU-Pro (Min/Max/Avg/Voting/ETTC)

94.21Average Score

Qwen-3-Thinking Ensemble

20.463639.609358.75577.9007May 29, 2026Jun 3, 2026Jun 9, 2026Jun 15, 2026Jun 20, 2026Jun 26, 2026Jul 2, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.05
94.2194.1294.3195.040.9519
2026.05
89.8681.1694.3194.820.9482
2026.05
87.7381.1694.3189.790.9467
2026.05
87.6481.1694.1289.340.9408
2026.06
57.37----
2026.07
45.2----
2026.07
43.7----
2026.07
43----
2026.07
42----
2026.07
41.8----
2026.07
41.6----
2026.07
41.4----
2026.07
41.2----
2026.07
40.2----
2026.07
40.2----
2026.07
40.1----
2026.07
40.1----
2026.07
39.8----
2026.07
39.8----
2026.07
39.4----
2026.07
39.2----
2026.07
39.1----
2026.07
39.1----
2026.07
38.8----
2026.07
38.6----
2026.07
38.3----
2026.07
38.2----
2026.07
37.9----
2026.07
37.6----
2026.07
37.4----
2026.07
37.3----
2026.06
35.16----
2026.06
34.65----
2026.06
34.64----
2026.07
32.7----
2026.07
32.5----
2026.07
32.4----
2026.07
32.3----
2026.07
32.3----
2026.07
32.2----
2026.07
31.8----
2026.07
31.8----
2026.07
31.8----
2026.07
31.7----
2026.07
31.6----
2026.07
31.3----
2026.07
30.9----
2026.07
25.1----
2026.07
24.9----
2026.07
24.8----
2026.07
24.6----
2026.07
24.5----
2026.07
24.5----
2026.07
24.4----
2026.07
24.4----
2026.07
24.3----
2026.07
24.2----
2026.07
24.2----
2026.07
24.2----
2026.07
23.3----