o3

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

ECI STANDING#60 of 266
SCORE146.91145.23–148.66 CI
FRONTIER LAGLaunched in the leadNothing released before it had scored higher.
SCORES LIKE THESE MODELSQwen3.5 397B-A17BAlibaba · Feb 2026146.96Claude Sonnet 4.5Anthropic · Sep 2025146.84
Qwen 3.5 Plus (hosted 397B-A17B)Alibaba · Feb 2026146.73
MiniMax-M2.5MiniMax · Feb 2026146.51
Full Epoch Capabilities Index ranking

From the lab

Launch announcement · Apr 16, 2025Introducing OpenAI o3 and o4-mini
RELEASE DATEApr 16, 2025
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.