List your company

Answer Verification on MATH

0.9128AUROCMSV 64
0.5510880.6449940.73890.832806Aug 11, 2025Sep 14, 2025Oct 18, 2025Nov 21, 2025Dec 25, 2025Jan 28, 2026Mar 3, 2026

Evaluation results

MethodLinks
MSV 64Sequences=64, Evaluation Protocol=Streaming2026.030.91280.1147
MSV 16N sequences=16, Weighted Voting=False2026.030.90620.1255
MSV 64N sequences=64, Weighted Voting=False2026.030.90490.1261
MSV 16Sequences=16, Evaluation Protocol=Streaming2026.030.90370.1104
MSV 4N sequences=4, Weighted Voting=False2026.030.89450.1348
MSV 4Sequences=4, Evaluation Protocol=Streaming2026.030.89170.1324
ProbeN sequences=1, Weighted Voting=False2026.030.8790.1346
Probe + WV 4Sequences=4, Evaluation Protocol=Weighted Voting2026.030.87690.1563
Probe + WV 16Sequences=16, Evaluation Protocol=Weighted Voting2026.030.87690.1563
Probe + WV 64Sequences=64, Evaluation Protocol=Weighted Voting2026.030.87690.1563
ProbeEvaluation Protocol=Streaming2026.030.8690.1592
MSV 1 + WV 4Sequences=4, Evaluation Protocol=MSV 1 + Weighted Voting2026.030.85670.1629
MSV 1 + WV 16Sequences=16, Evaluation Protocol=MSV 1 + Weighted Voting2026.030.85670.1629
MSV 1 + WV 64Sequences=64, Evaluation Protocol=MSV 1 + Weighted Voting2026.030.85670.1629
MSV 1N sequences=1, Weighted Voting=False2026.030.85660.146
MSV 1Sequences=1, Evaluation Protocol=Streaming2026.030.84430.1601
MSV 1 + WV 64N sequences=64, Weighted Voting=True2026.030.83640.138
Probe + WV 64N sequences=64, Weighted Voting=True2026.030.83460.137
Probe(EOS)Model=Gemma3-12B2025.080.834—
Probe(AVG)Model=Fanar1-9b2025.080.833—
Prob(Exact)Model=Fanar1-9b2025.080.827—
Probe + WV 16N sequences=16, Weighted Voting=True2026.030.82280.1416
MSV 1 + WV 16N sequences=16, Weighted Voting=True2026.030.82280.1425
Probe(EU)Model=Fanar1-9b2025.080.794—
Probe + WV 4N sequences=4, Weighted Voting=True2026.030.7930.1649
MSV 1 + WV 4N sequences=4, Weighted Voting=True2026.030.7920.1656
LogTokUModel=Gemma3-12B2025.080.791—
Probe(EOS)Model=Fanar1-9b2025.080.79—
Probe(AVG)Model=Gemma3-12B2025.080.786—
P(true)Model=Gemma3-12B2025.080.779—
Prob(Exact)Model=Gemma3-12B2025.080.773—
LogProbModel=Fanar1-9b2025.080.757—
Probe(EOS)Model=Qwen2.5-7B2025.080.703—
Probe(AVG)Model=Qwen2.5-7B2025.080.699—
LogProbModel=Gemma3-12B2025.080.683—
Probe(EU)Model=Gemma3-12B2025.080.669—
LogTokUModel=Fanar1-9b2025.080.666—
P(true)Model=Qwen2.5-7B2025.080.664—
Probe(EU)Model=Qwen2.5-7B2025.080.646—
P(true)Model=Fanar1-9b2025.080.635—
LogProbModel=Qwen2.5-7B2025.080.635—
Prob(Exact)Model=Qwen2.5-7B2025.080.627—
LogTokUModel=Qwen2.5-7B2025.080.565—