Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math & physics reasoning on OlympiadBench Phys
Loading...
14.41
Accuracy
INFUSER
10.0004
11.1452
12.29
13.4348
Jun 8, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
INFUSER
Model Backbone=Qwen3-8...
2026.06
14.41
R-Zero
Model Backbone=Qwen3-8...
2026.06
13.98
AZR
Model Backbone=Qwen3-8...
2026.06
13.14
Base
Model Backbone=Qwen3-8...
2026.06
12.29
R-Zero
Model Backbone=Qwen3-4...
2026.06
11.44
INFUSER
Model Backbone=Qwen3-4...
2026.06
10.31
Base
Model Backbone=Qwen3-4...
2026.06
10.17
AZR
Model Backbone=Qwen3-4...
2026.06
10.17
Feedback
Search any
task
Search any
task