o1 vs o3
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | o1 | o3 |
|---|---|---|
| Coding | 6.9 o1 | 7.8 o3 |
| Agents | 19.5* o1 | 8.3 o3 |
| Reasoning | 23.9 o1 | 38.1 o3 |
| Knowledge & language | 40.9 o1 | 49.3 o3 |
| Human preference | 44.7* o1 | 49.1 o3 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
o3 leads on 9 of the 9 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | o1 | o3 |
|---|---|---|
| Chess Puzzles (Epoch AI) | 11% | 37% |
| AIME 2025 | 81.7% | 89.2% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 14.7% | 33.3% |
| GPQA Diamond | 75.7% | 81.8% |
| MATH Level 5 (Epoch AI) | 94.7% | 97.8% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 73.3% | 84.4% |
| SimpleBench (SimpleBench) | 40.1% | 53.1% |
| SimpleQA Verified | 41.1% | 49.4% |
| WeirdML (Håvard Tveit Ihle) | 46.1% | 52.4% |
FAQ
Is o1 better than o3?
o3 scores 25.8 on the Respan Index (#107), ahead of o1 at 23.4 (#110). o3 leads on 9 of the 9 benchmarks both report.
Which is cheaper, o1 or o3?
o1 lists at $15 input and $60 output per 1M tokens; o3 at $2 and $8. o3 is 7.5x cheaper per token at list price.
Which has the larger context window?
Both accept 200K tokens of context.