List your company

Question Answering on MMLU-Pro (Non-trivial subset All 14 subjects, test)

33.93Accuracyoracle (pass@16)
27.762829.363930.96532.5661Jun 6, 2026

Evaluation results

MethodLinks
oracle (pass@16)Solver=Qwen3-1.7B, Temperature=0.7, Samples per question=128, Embeddings=Qwen3-Embedding-8B, Number of voters=162026.0633.935.93
PPV confidenceSolver=Qwen3-1.7B, Temperature=0.7, Samples per question=128, Embeddings=Qwen3-Embedding-8B, Number of voters=16, Mode=confidence2026.0630.242.24
PPV divSolver=Qwen3-1.7B, Temperature=0.7, Samples per question=128, Embeddings=Qwen3-Embedding-8B, Number of voters=16, Mode=div2026.0629.831.83
PPV inverted x divSolver=Qwen3-1.7B, Temperature=0.7, Samples per question=128, Embeddings=Qwen3-Embedding-8B, Number of voters=16, Mode=inverted x div2026.0629.521.52
majoritySolver=Qwen3-1.7B, Temperature=0.7, Samples per question=128, Embeddings=Qwen3-Embedding-8B, Number of voters=162026.0628—