Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on OlyBench Math
Loading...
4.7
Acceptance Length
TTS
1.164
2.082
3
3.918
May 10, 2026
Acceptance Length
Delta Percentage
Updated 22d ago
Evaluation Results
Method
Method
Links
Acceptance Length
Delta Percentage
TTS
Target Model=Qwen/Qwen...
2026.05
4.7
40.2
TTS
Target Model=Qwen/Qwen...
2026.05
4.4
48.9
TTS
Target Model=Qwen/Qwen...
2026.05
4.1
50.3
DFlash
Target Model=Qwen/Qwen...
2026.05
3.4
-
DFlash
Target Model=Qwen/Qwen...
2026.05
3
-
DFlash
Target Model=Qwen/Qwen...
2026.05
2.7
-
TTS
Model=Llama3.1-8B
2026.05
2.1
66.8
TTS
Model=Qwen/Qwen3-8B
2026.05
1.9
18.5
TTS
Model=Qwen/Qwen3-32B
2026.05
1.9
24.5
EAGLE-3
Model=Qwen/Qwen3-8B
2026.05
1.6
-
EAGLE-3
Model=Qwen/Qwen3-32B
2026.05
1.5
-
EAGLE-3
Model=Llama3.1-8B
2026.05
1.3
-
Feedback
Search any
task
Search any
task