List your company

Scientific Problem Solving on SciBench (Diff, Stat, Calc metrics)

65.47Diff AccuracyMeta-reasoner
54.872457.623760.37563.1263Feb 27, 2025

Evaluation results

MethodLinks
Meta-reasonerModel=gemini-exp-12062025.0265.4779.4282.77
Meta-reasonerModel=gpt-4o-mini2025.0260.3273.6480.23
HiAR-ICLModel=gemini-exp-12062025.0257.7675.9280.23
HiAR-ICLModel=gpt-4o-mini2025.0257.4270.1277.93
Evo-PromptModel=gemini-exp-12062025.0257.3270.3278.42
Evo-PromptModel=gpt-4o-mini2025.0255.2867.3276.53