This model is 19 months old. The same company has since released something newer: GPT-Live-1.1 (2026-11-21). The details below are still accurate for this model. It just is not what we would recommend today.
o3
OpenAIπΊπΈ United States
OpenAI reasoning model for math, code and science.
Context window200K tokens
Input / 1M tokens$10
Output / 1M tokens$40
Version History
launchmajor
o3 released. OpenAI reasoning model for math, code and science.
Benchmark Scores
Full leaderboard β| Benchmark | Score | Rank | Source |
|---|---|---|---|
| Arena Elo | 1432 Elo | 80 of 146 | LMArena, Nov 2026 β |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.