Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME24 (A24 Score)
Loading...
53.3
A24 Score
GEAR
35.62
40.21
44.8
49.39
May 12, 2026
A24 Score
Updated 21d ago
Evaluation Results
Method
Method
Links
A24 Score
GEAR
Backbone=Qwen3-4B, Eva...
2026.05
53.3
GEAR
Backbone=Qwen3-8B, Eva...
2026.05
51.4
GEAR
Backbone=Qwen3-4B, Eva...
2026.05
50.3
ARPO
Backbone=Qwen3-8B, Eva...
2026.05
47.9
Base
Backbone=Qwen3-8B, Eva...
2026.05
47.1
OPSD+RL
Backbone=Qwen3-8B, Eva...
2026.05
47.1
GRPO
Backbone=Qwen3-8B, Eva...
2026.05
46.5
ARPO
Backbone=Qwen3-4B, Eva...
2026.05
46.3
Base
Backbone=Qwen3-4B, Eva...
2026.05
45.8
MT-GRPO
Backbone=Qwen3-8B, Eva...
2026.05
45.5
GRPO
Backbone=Qwen3-4B, Eva...
2026.05
45.3
GRPO
Backbone=Qwen3-4B, Eva...
2026.05
43.1
MT-GRPO
Backbone=Qwen3-4B, Eva...
2026.05
42.3
OPSD+RL
Backbone=Qwen3-4B, Eva...
2026.05
39.6
OPSD
Backbone=Qwen3-8B, Eva...
2026.05
38.1
OPSD
Backbone=Qwen3-4B, Eva...
2026.05
36.3
Feedback
Search any
task
Search any
task