List your company

Mathematical Reasoning on LiveBench-Math July 30, 2025 snapshot (test)

66.9AccuracyGTBP
55.106458.168261.2364.2918Jun 12, 2026

Evaluation results

MethodLinks
GTBPBackbone=GPT-4.1-mini, Number of intermediate modules K=tuned over {1, 2, 4}, Mini-batch size=15, Number of iterations=152026.0666.9
GEPABackbone=GPT-4.1-mini, Implementation=DSPy2026.0664.13
Zero-shotBackbone=GPT-4.1-mini, Shot mode=zero-shot2026.0661.11
Few-shotBackbone=GPT-4.1-mini, Shot mode=few-shot, Number of examples=tuned over {1, 3, 5, 10}2026.0655.56