Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical and Scientific Reasoning on OlympiadBench
Loading...
50.24
Mean Accuracy
INFUSER
34.7128
38.7439
42.775
46.8061
Apr 13, 2026
Apr 22, 2026
May 1, 2026
May 11, 2026
May 20, 2026
May 29, 2026
Jun 8, 2026
Mean Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Accuracy
INFUSER
Model Backbone=Qwen3-8...
2026.06
50.24
AZR
Model Backbone=Qwen3-8...
2026.06
47.92
R-Few
Model Backbone=Qwen3-8...
2026.06
46.4
R-Zero
Model Backbone=Qwen3-8...
2026.06
45.1
Qwen2.5 32B + RL (synthetic)
Model Size=32B, Post-t...
2026.04
44.53
R-Zero
Model Backbone=Qwen3-4...
2026.06
43.18
AZR
Model Backbone=Qwen3-4...
2026.06
43.18
R-Few
Model Backbone=Qwen3-4...
2026.06
42.8
SPICE
Model Backbone=Qwen3-4...
2026.06
42.7
SPICE
Model Backbone=Qwen3-8...
2026.06
42.5
INFUSER
Model Backbone=Qwen3-4...
2026.06
42.38
Qwen2.5 32B
Model Size=32B, Varian...
2026.04
41.41
Base
Model Backbone=Qwen3-8...
2026.06
40.36
Base
Model Backbone=Qwen3-4...
2026.06
35.31
Feedback
Search any
task
Search any
task