o1 Preview vs o3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
o1 Preview—
o320.1
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
o1 Preview1,366
o31,383
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
o1 Preview—
o370.1
| Benchmark | o1 Preview | o3 |
|---|---|---|
| Humanity's Last Exam | — | 20.1 |
| Arena Text · creative writing | 1,366 | 1,383 |
| MMMU-Pro (vision) | — | 70.1 |
Specs
| Spec | o1 Preview | o3 |
|---|---|---|
| Input, per 1M | — | $2 |
| Output, per 1M | — | $8 |
| Speed, tok/s | — | 126 |
| Context | — | 200K |
| Weights | Not verified | Closed |
| Released | Sep 2024 | Apr 2025 |
| See images | ? | ✓ |
| Read PDFs | ? | Partial |
| Hear audio | ? | — |
| Watch video | ? | — |
| Call tools | ? | ✓ |
| Force a tool call | ? | Partial |
| Return strict JSON | ? | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
o1 Preview → o3
Nothing known.
o3 → o1 Preview