AI Benchmark Digest — 2026-05-05
AI Benchmark Digest — 2026-05-05
=== DAILY === NEW BENCHMARKS (2) - MathArena - ARXIV_FALSE April (Accuracy (%)): leader GPT-5.5 (xhigh) (72.13), 6 models - MathArena - ARXIV April (Accuracy (%)): leader GPT-5.5 (xhigh) (59.78), 6 models
NEW #1 LEADERS (2) - Kaggle FACTS Parametric (Score (%)): GPT-5.5 (78.04) beat Gemini 3 Flash Preview (72.26) by 5.78 - Kaggle FACTS (Google) (Avg Score (%)): GPT-5.5 (71.19) beat Gemini 3.1 Pro Preview (67.71) by 3.48
Don't miss what's next. Subscribe to Mikhail Doroshenko: