STEM Theorem Question Answering on TheoremQA
4.4Acceptance LengthTTS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TTSTarget Model=Qwen/Qwen3-4B2026.05 | 4.4 | 23.4 | |
| TTSTarget Model=Qwen/Qwen3-8B2026.05 | 4.3 | 22.8 | |
| TTSTarget Model=Qwen/Qwen3.5-122B2026.05 | 4.2 | 25.1 | |
| DFlashTarget Model=Qwen/Qwen3-4B2026.05 | 3.6 | — | |
| DFlashTarget Model=Qwen/Qwen3-8B2026.05 | 3.5 | — | |
| DFlashTarget Model=Qwen/Qwen3.5-122B2026.05 | 3.3 | — | |
| TTSModel=Llama3.1-8B2026.05 | 1.9 | 56.9 | |
| TTSModel=Qwen/Qwen3-8B2026.05 | 1.9 | 16.8 | |
| TTSModel=Qwen/Qwen3-32B2026.05 | 1.8 | 21.9 | |
| EAGLE-3Model=Qwen/Qwen3-8B2026.05 | 1.6 | — | |
| EAGLE-3Model=Qwen/Qwen3-32B2026.05 | 1.5 | — | |
| EAGLE-3Model=Llama3.1-8B2026.05 | 1.2 | — |