Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on AIME 2025 (Speedup, Mean acceptance length τ)
Loading...
7.23
Speedup
DFlash+DDTree
3.0076
4.1038
5.2
6.2962
Apr 14, 2026
Speedup
Mean Acceptance Length (τ)
Updated 3d ago
Evaluation Results
Method
Method
Links
Speedup
Mean Acceptance Length (τ)
DFlash+DDTree
Model=Qwen3-4B, Temper...
2026.04
7.23
10.23
DFlash+DDTree
Model=Qwen3-8B, Temper...
2026.04
6.99
9.86
DFlash+DDTree
Model=Qwen3-Coder-30B-...
2026.04
5.88
7.63
DFlash
Model=Qwen3-4B, Temper...
2026.04
5.33
7.37
DFlash
Model=Qwen3-8B, Temper...
2026.04
5.32
7.39
DFlash+DDTree
Model=Qwen3-8B, Temper...
2026.04
5.25
7.71
DFlash+DDTree
Model=Qwen3-4B, Temper...
2026.04
5.08
7.22
DFlash+DDTree
Model=Qwen3-Coder-30B-...
2026.04
4.98
6.62
DFlash
Model=Qwen3-Coder-30B-...
2026.04
3.98
5.13
DFlash
Model=Qwen3-4B, Temper...
2026.04
3.38
4.79
DFlash
Model=Qwen3-8B, Temper...
2026.04
3.36
4.79
DFlash
Model=Qwen3-Coder-30B-...
2026.04
3.17
4.26
Feedback
Search any
task
Search any
task