Model comparison
o1-pro vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 31.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. o1-pro scores higher in 1 category and o3-pro in 1 category; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where o3-pro leads 23.8 to 20.4.
- The biggest single-benchmark swing is ARC-AGI-1: 23.3% for o1-pro and 59.3% for o3-pro.
- o3-pro is cheaper at $20 / $80 per million input/output tokens, against $150 / $600 for o1-pro.
Side by side
| o1-pro | o3-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 31.5 | 42.9 |
| Released | 2025-03-19 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 100K | 100K |
| Input $ / M tokens | $150 | $20 |
| Output $ / M tokens | $600 | $80 |
| Results tracked | 3 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
o1-pro: —, o3-pro: 55.5 (#24)
| Benchmark | o1-pro | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
Reasoning o3-pro leads
o1-pro: 20.4 (#239), o3-pro: 23.8 (#171)
| Benchmark | o1-pro | o3-pro |
|---|---|---|
| ARC-AGI-1 | 23.3% | 59.3% |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| EnigmaEval | 6.1% | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.42 |
Knowledge Too close to call
o1-pro: 29.7 (#234), o3-pro: 29.5 (#238)
| Benchmark | o1-pro | o3-pro |
|---|---|---|
| Humanity's Last Exam | 8.1% | — |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
Long Context Not comparable
o1-pro: —, o3-pro: 72.2 (#1)
| Benchmark | o1-pro | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
Writing & Preference Not comparable
o1-pro: —, o3-pro: 57.1 (#133)
| Benchmark | o1-pro | o3-pro |
|---|---|---|
| Short-Story Creative Writing | — | 84.4% |
Frequently asked questions
Is o1-pro better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 31.5 on the Noometry Index.
Which is cheaper, o1-pro or o3-pro?
o3-pro is cheaper. It lists at $20 per million input tokens and $80 per million output tokens; o1-pro lists at $150 and $600.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do o1-pro and o3-pro share?
1 benchmark has published results for both models. o1-pro has 3 scored results on Noometry and o3-pro has 12.