Spoken Mathematics Reasoning on VoxEval College 1.0 (test)
65AccuracyCoT
Evaluation Results
| Method | Links | |
|---|---|---|
| CoTModel=Qwen2.5, Hyperparams. (k, α)=-2026.03 | 65 | |
| SGSModel=Qwen2.5, Hyperparams. (k, α)=4, 0.0252026.03 | 65 | |
| TGSModel=Qwen2.5, Hyperparams. (k, α)=3, 0.052026.03 | 64 | |
| VanillaModel=Qwen2.5, Hyperparams. (k, α)=3, 0.0252026.03 | 56 | |
| NormalModel=Qwen2.5, Hyperparams. (k, α)=-2026.03 | 40 | |
| CoTModel=Phi4-mm, Hyperparams. (k, α)=-2026.03 | 36 | |
| VanillaModel=Phi4-mm, Hyperparams. (k, α)=5, 0.0252026.03 | 35 | |
| VanillaModel=Voxtral, Hyperparams. (k, α)=5, 0.0252026.03 | 32 | |
| SGSModel=Phi4-mm, Hyperparams. (k, α)=3, 0.052026.03 | 30 | |
| TGSModel=Phi4-mm, Hyperparams. (k, α)=3, 0.0252026.03 | 30 | |
| SGSModel=Voxtral, Hyperparams. (k, α)=3, 0.12026.03 | 29.3 | |
| NormalModel=Voxtral, Hyperparams. (k, α)=-2026.03 | 29 | |
| CoTModel=AF3, Hyperparams. (k, α)=-2026.03 | 27.4 | |
| CoTModel=Voxtral, Hyperparams. (k, α)=-2026.03 | 26.3 | |
| TGSModel=Voxtral, Hyperparams. (k, α)=4, 0.0252026.03 | 26.3 | |
| NormalModel=AF3, Hyperparams. (k, α)=-2026.03 | 26.1 | |
| NormalModel=Phi4-mm, Hyperparams. (k, α)=-2026.03 | 26 | |
| SGSModel=AF3, Hyperparams. (k, α)=1, 0.0252026.03 | 24 | |
| VanillaModel=AF3, Hyperparams. (k, α)=3, 0.12026.03 | 20 | |
| TGSModel=AF3, Hyperparams. (k, α)=5, 0.12026.03 | 20 |