Mathematical Reasoning on OlyBench Math
4.7Acceptance LengthTTS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| TTSTarget Model=Qwen/Qwen3.5-122B2026.05 | 4.7 | 40.2 | |
| TTSTarget Model=Qwen/Qwen3-4B2026.05 | 4.4 | 48.9 | |
| TTSTarget Model=Qwen/Qwen3-8B2026.05 | 4.1 | 50.3 | |
| DFlashTarget Model=Qwen/Qwen3.5-122B2026.05 | 3.4 | — | |
| DFlashTarget Model=Qwen/Qwen3-4B2026.05 | 3 | — | |
| DFlashTarget Model=Qwen/Qwen3-8B2026.05 | 2.7 | — | |
| TTSModel=Llama3.1-8B2026.05 | 2.1 | 66.8 | |
| TTSModel=Qwen/Qwen3-8B2026.05 | 1.9 | 18.5 | |
| TTSModel=Qwen/Qwen3-32B2026.05 | 1.9 | 24.5 | |
| EAGLE-3Model=Qwen/Qwen3-8B2026.05 | 1.6 | — | |
| EAGLE-3Model=Qwen/Qwen3-32B2026.05 | 1.5 | — | |
| EAGLE-3Model=Llama3.1-8B2026.05 | 1.3 | — |