List your company

Mathematical Reasoning on GSM8K (test) (Accuracy, Avg rounds, Avg calls, Wall (s), n)

99AccuracyB1 (3-sample vote)
96.9297.469898.54May 18, 2026

Evaluation results

MethodLinks
B1 (3-sample vote)Protocol=B1, Agents=GPT-5, Claude-Opus-4-6, Gemini-2.5-Pro, Judge=Claude-Opus-4-62026.05991310200
B2 (Fixed-5 baseline)Protocol=B2, Agents=GPT-5, Claude-Opus-4-6, Gemini-2.5-Pro, Judge=Claude-Opus-4-62026.059951542.2199
B3 (Wald-SPRT)Protocol=B3, Agents=GPT-5, Claude-Opus-4-6, Gemini-2.5-Pro, Judge=Claude-Opus-4-6, alpha=0.05, beta=0.05, Rmax=82026.05971.014.0612.1200