Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME25 (EM, #Tool)
Loading...
33.3
EM Accuracy
ParetoPO
9.068
15.359
21.65
27.941
Jun 15, 2026
EM Accuracy
Tool Usage Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM Accuracy
Tool Usage Rate
ParetoPO
Base Model=Qwen2.5-Mat...
2026.06
33.3
0.8
ParetoPO
Base Model=Qwen2.5-Mat...
2026.06
30
0.8
ToRL-GRPO
Base Model=Qwen2.5-Mat...
2026.06
26.7
2.1
ToRL-GRPO
Base Model=Qwen2.5-Mat...
2026.06
23.3
2.3
OTC-GRPO
Base Model=Qwen2.5-Mat...
2026.06
23.3
0.8
MO-GRPO
Base Model=Qwen2.5-Mat...
2026.06
23.3
1.9
OTC-GRPO
Base Model=Qwen2.5-Mat...
2026.06
20
1.1
MO-GRPO
Base Model=Qwen2.5-Mat...
2026.06
16.7
1.8
Qwen2.5-Math-7B-Ins
Base Model=Qwen2.5-Mat...
2026.06
16.7
-
Qwen2.5-Math-7B-Ins-TIR
Base Model=Qwen2.5-Mat...
2026.06
16.7
1.4
Qwen2.5-Math-1.5B-Ins-TIR
Base Model=Qwen2.5-Mat...
2026.06
13.3
1.4
Qwen2.5-Math-1.5B-Ins
Base Model=Qwen2.5-Mat...
2026.06
10
-
Feedback
Search any
task
Search any
task