List your company

Spoken Mathematics Reasoning on VoxEval Elementary 1.0 (test)

84.7AccuracySGS
23.65239.50155.3571.199Mar 15, 2026

Evaluation results

MethodLinks
SGSModel=Qwen2.5, Hyperparams. (k, α)=4, 0.0252026.0384.7
VanillaModel=Qwen2.5, Hyperparams. (k, α)=3, 0.0252026.0383.9
TGSModel=Qwen2.5, Hyperparams. (k, α)=3, 0.052026.0383.6
CoTModel=Qwen2.5, Hyperparams. (k, α)=-2026.0383
TGSModel=Phi4-mm, Hyperparams. (k, α)=3, 0.0252026.0371.4
CoTModel=Phi4-mm, Hyperparams. (k, α)=-2026.0369.6
VanillaModel=Phi4-mm, Hyperparams. (k, α)=5, 0.0252026.0369.1
VanillaModel=Voxtral, Hyperparams. (k, α)=5, 0.0252026.0368.8
SGSModel=Phi4-mm, Hyperparams. (k, α)=3, 0.052026.0368.8
CoTModel=Voxtral, Hyperparams. (k, α)=-2026.0367.4
TGSModel=Voxtral, Hyperparams. (k, α)=4, 0.0252026.0367.1
SGSModel=Voxtral, Hyperparams. (k, α)=3, 0.12026.0365.8
NormalModel=Voxtral, Hyperparams. (k, α)=-2026.0356.9
NormalModel=Qwen2.5, Hyperparams. (k, α)=-2026.0352.1
TGSModel=AF3, Hyperparams. (k, α)=5, 0.12026.0342.9
VanillaModel=AF3, Hyperparams. (k, α)=3, 0.12026.0337.6
SGSModel=AF3, Hyperparams. (k, α)=1, 0.0252026.0336
NormalModel=Phi4-mm, Hyperparams. (k, α)=-2026.0333.1
CoTModel=AF3, Hyperparams. (k, α)=-2026.0330.4
NormalModel=AF3, Hyperparams. (k, α)=-2026.0326