Spoken Mathematics Reasoning on VoxEval High School 1.0 (test)
81.9AccuracyTGS
Evaluation Results
| Method | Links | |
|---|---|---|
| TGSModel=Qwen2.5, Hyperparams. (k, α)=3, 0.052026.03 | 81.9 | |
| SGSModel=Qwen2.5, Hyperparams. (k, α)=4, 0.0252026.03 | 80.7 | |
| CoTModel=Qwen2.5, Hyperparams. (k, α)=-2026.03 | 79.9 | |
| VanillaModel=Qwen2.5, Hyperparams. (k, α)=3, 0.0252026.03 | 79.6 | |
| TGSModel=Phi4-mm, Hyperparams. (k, α)=3, 0.0252026.03 | 48.9 | |
| VanillaModel=Phi4-mm, Hyperparams. (k, α)=5, 0.0252026.03 | 47 | |
| SGSModel=Phi4-mm, Hyperparams. (k, α)=3, 0.052026.03 | 47 | |
| NormalModel=Qwen2.5, Hyperparams. (k, α)=-2026.03 | 45.6 | |
| SGSModel=Voxtral, Hyperparams. (k, α)=3, 0.12026.03 | 43.9 | |
| VanillaModel=Voxtral, Hyperparams. (k, α)=5, 0.0252026.03 | 43.3 | |
| CoTModel=Voxtral, Hyperparams. (k, α)=-2026.03 | 42 | |
| CoTModel=Phi4-mm, Hyperparams. (k, α)=-2026.03 | 41.9 | |
| TGSModel=Voxtral, Hyperparams. (k, α)=4, 0.0252026.03 | 41.3 | |
| NormalModel=Voxtral, Hyperparams. (k, α)=-2026.03 | 36.7 | |
| NormalModel=AF3, Hyperparams. (k, α)=-2026.03 | 28.2 | |
| NormalModel=Phi4-mm, Hyperparams. (k, α)=-2026.03 | 24.8 | |
| CoTModel=AF3, Hyperparams. (k, α)=-2026.03 | 24.2 | |
| TGSModel=AF3, Hyperparams. (k, α)=5, 0.12026.03 | 24.1 | |
| VanillaModel=AF3, Hyperparams. (k, α)=3, 0.12026.03 | 22.2 | |
| SGSModel=AF3, Hyperparams. (k, α)=1, 0.0252026.03 | 21.1 |