o3 Medium
| Released | 2025-04-16 |
|---|---|
| Price per 1M | $2.00 in · $8.00 out |
| Overall score | 50.1 · rank 262 |
| Context window | 200,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Medium |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 50.1 | 262 | 16 |
| Overall: Coding | 49.6 | 264 | 11 |
| Overall: Reasoning | 51.5 | 243 | 9 |
| Overall: Agentic work | 48.9 | 286 | 11 |
| Overall: Frontend | 50.3 | 213 | 4 |
| Coding | 49.8 | 246 | 2 |
| Agents | 47.9 | 217 | 3 |
| Reasoning | 51.4 | 247 | 6 |
| Math | 51.9 | 162 | 2 |
| Knowledge | 50.9 | 119 | 1 |
| Multimodal | 51.8 | 104 | 2 |
| Value vs price | −3.7 | 296 |
Evidence
Coding 49.8 ±1.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 76.9% | Epoch AI | 2026-11-11 |
| SWE-bench Verified (Epoch run) | 62.3% | Epoch AI | 2026-02-12 |
Agents 47.9 ±3.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OSWorld (v1) | 23.0% | Epoch AI | 2026-11-11 |
| METR task suite | 65.4% | Epoch AI | 2026-11-11 |
| DeepResearch Bench | 45.2% | Epoch AI | 2026-11-11 |
Reasoning 51.4 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 80.8% | Epoch AI | 2026-08-07 |
| ARC-AGI-2 | 3.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 3.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 53.8% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 53.8% | Epoch AI | 2026-11-11 |
| EnigmaEval | 13.1% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 37.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 23.0% | Epoch AI | 2026-08-27 |
Math 51.9 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 29.8% | Epoch AI | 2026-08-27 |
| FrontierMath Tiers 1-3 (2025 set) | 16.9% | Epoch AI | 2025-11-16 |
| OTIS Mock AIME 2024-2025 | 84.4% | Epoch AI | 2026-08-07 |
Knowledge 50.9 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 19.2% | Epoch AI | 2026-11-11 |
Multimodal 51.8 ±5.1
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| OSWorld (v1) | 17.2% | Epoch AI | Lower duplicate run on the same benchmark |
| OSWorld (v1) | 9.1% | Epoch AI | Lower duplicate run on the same benchmark |
Names matched to this model
o3-medium