List your company

Question Answering on MMLU-Pro (Adversarial Setting, test)

98.9AccuracyMA-Reasoning (ECL E)
96.61297.20697.898.394Jan 29, 2026

Evaluation results

MethodLinks
MA-Reasoning (ECL E)Backbone=Gemini 3 Pro2026.0198.9
MA-Outcome (ECL I)Backbone=Gemini 3 Flash2026.0196.7