Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME (Speedup)
Loading...
4.4
Speedup
FailFast
1.3008
2.1054
2.91
3.7146
Dec 23, 2025
Speedup
Updated 3mo ago
Evaluation Results
Method
Method
Links
Speedup
FailFast
Target Model=Qwen2.5-3...
2025.12
4.4
FailFast
Target Model=Qwen2.5-1...
2025.12
3.37
Fast-dLLM
Target Model=Qwen2.5-3...
2025.12
3.29
EAGLE-3 (w/ draft tree)
Target Model=Qwen2.5-3...
2025.12
2.85
AR Draft Model
Target Model=Qwen2.5-3...
2025.12
2.84
FailFast
Target Model=Qwen2.5-7...
2025.12
2.63
EAGLE-3 (w/ draft tree)
Target Model=Qwen2.5-1...
2025.12
2.38
EAGLE-3 (w/ draft tree)
Target Model=Qwen2.5-7...
2025.12
2.36
Fast-dLLM
Target Model=Qwen2.5-1...
2025.12
2.22
AR Draft Model
Target Model=Qwen2.5-1...
2025.12
1.94
Fast-dLLM
Target Model=Qwen2.5-7...
2025.12
1.57
AR Draft Model
Target Model=Qwen2.5-7...
2025.12
1.42
Feedback
Search any
task
Search any
task