o1

O-series reasoning model for hard analysis, math, coding, and planning

ECI STANDING#97 of 266
SCORE141.86140.15–143.11 CI
FRONTIER LAGLaunched in the leadNothing released before it had scored higher.
SCORES LIKE THESE MODELSClaude Haiku 4.5Anthropic · Oct 2025142.37
Gemma 4 26B A4BGoogle DeepMind · Apr 2026141.86
Claude Sonnet 4Anthropic · May 2025141.69
Gemini 2.5 Flash (May 2025)Google DeepMind · May 2025141.54
Full Epoch Capabilities Index ranking

From the lab

Launch announcement · Sep 12, 2024Introducing OpenAI o1Related article · Dec 17, 2024OpenAI o1 and new tools for developers
RELEASE DATESep 12, 2024
WEIGHTSClosed weights
CONTEXT WINDOW200K
MAX OUTPUT100K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image, pdf
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.