o1

openai · Ranked across 4 benchmarks · best rank #4

Benchmark scores

BenchmarkCategoryRankScoreCaptured
METR Task Horizon (HCAST) agents #4 51m 2025-07-12
Aider Polyglot code #10 61.7% 2024-12-21
Chatbot Arena chat #32 1366 2026-04-30
OpenRouter · Weekly Usage usage #49 #340 2026-05-02