o3-mini
| Released | 2024-12-20 |
|---|---|
| Price per 1M | $1.10 in · $4.40 out |
| Overall score | 45.2 · rank 156 |
| Context window | 200,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 45.2 | 156 | 18 |
| Overall: Coding | 44.9 | 156 | 11 |
| Overall: Reasoning | 46.7 | 144 | 13 |
| Overall: Agentic work | 45.3 | 152 | 11 |
| Overall: Frontend | 44.6 | 142 | 4 |
| Coding | 44.6 | 160 | 4 |
| Reasoning | 46.6 | 141 | 7 |
| Math | 49.4 | 118 | 4 |
| Knowledge | 42.0 | 135 | 2 |
| General | 43.3 | 147 | 1 |
| Value vs price | −4.6 | 158 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 41.1 ±7.0 | 1 |
| High | 45.2 ±2.4 | 18 |
| Low | 41.8 ±3.6 | 7 |
| Medium | 45.2 ±3.3 | 8 |
Evidence
Coding 44.6 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 60.4% | Epoch AI | 2026-11-11 |
| GSO | 1.3% | Epoch AI | 2026-11-11 |
| SciCode | 42.8% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 71.5% | Vals AI | 2026-09-01 |
Reasoning 46.6 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 3.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 3.0% | ARC Prize | 2026-11-11 |
| CritPt | 0.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 34.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 34.5% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 77.0% | Epoch AI | 2025-02-13 |
| GPQA Diamond (Vals run) | 75.5% | Vals AI | 2026-09-01 |
| Chess Puzzles | 15.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 22.8% | SimpleBench | 2026-11-11 |
| SimpleBench | 22.8% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 7.0% | Epoch AI | 2026-08-27 |
Math 49.4 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 18.6% | Epoch AI | 2026-06-11 |
| MATH Level 5 | 96.5% | Epoch AI | 2025-02-13 |
| FrontierMath Tier 4 | 0.0% | Epoch AI | 2026-06-11 |
| OTIS Mock AIME 2024-2025 | 76.9% | Epoch AI | 2025-02-27 |
| FrontierMath Tiers 1-3 (2025 set) | 12.4% | Epoch AI | 2025-11-16 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2025-07-01 |
Knowledge 42.0 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 15.3% | Epoch AI | 2026-08-31 |
| MMLU-Pro (Vals run) | 78.7% | Vals AI | 2026-09-01 |
General 43.3 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,364 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 14.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 22.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 14.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 22.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 0.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 2.1% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 0.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 2.1% | ARC Prize | A stronger configuration result was used |
| Aider Polyglot | 53.8% | Epoch AI | A stronger configuration result was used |
| Chess Puzzles | 6.0% | Epoch AI | A stronger configuration result was used |
| Chess Puzzles | 11.0% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 | 3.9% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 | 10.5% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 8.1% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 68.2% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 74.3% | Epoch AI | A stronger configuration result was used |
| GSO | 1.3% | Epoch AI | A stronger configuration result was used |
| LMArena Text | 1,348 | LMArena | A stronger configuration result was used |
| MATH Level 5 | 95.2% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 44.4% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 63.9% | Epoch AI | A stronger configuration result was used |
Names matched to this model
o3-mini, o3-mini-2025-01-31