# o1 vs o1-mini

> o1 is the stronger model overall, scoring 40.9 to 34.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o1-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. o1 scores higher in 8 categories and o1-mini in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where o1 leads 27.9 to 8.8.
- The biggest single-benchmark swing is Aider Polyglot: 61.7% for o1 and 32.9% for o1-mini.

## Snapshot

| | o1 | o1-mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 40.9 | 34.0 |
| Rank | 143 | 235 |
| Context | 200K | — |
| Input $/M | $15 | — |
| Output $/M | $60 | — |
| Weights | Proprietary | Proprietary |

## Coding

- o1: 46.1 (#70)
- o1-mini: 35.5 (#224)

| Benchmark | o1 | o1-mini |
|---|---|---|
| Aider Polyglot | 61.7% | 32.9% |
| WeirdML | 47.6% | 36.3% |
| LiveBench Coding | 69.7% | 48% |
| LMArena Coding | 1367 | 1362 |
| HumanEval+ | 89% | 89% |
| MBPP+ | 80.2% | 78.8% |
| CadEval | 56% | — |

## Agentic & Tool Use

- o1: 24.6 (#117)
- o1-mini: 24.6 (#118)

| Benchmark | o1 | o1-mini |
|---|---|---|
| Cybench | 10% | 10% |
| METR Time Horizons | 51.1% | — |

## Reasoning

- o1: 27.9 (#111)
- o1-mini: 8.8 (#346)

| Benchmark | o1 | o1-mini |
|---|---|---|
| SimpleBench | 41.7% | 18.1% |
| ARC-AGI-1 | 30.7% | 14% |
| LiveBench Reasoning | 91.6% | 72.3% |
| LMArena Hard Prompts | 1371 | 1333 |
| LiveBench Data Analysis | 65.5% | 57.9% |
| Epoch Capabilities Index | 141.91 | 135.82 |
| LiveBench | 75.7% | 57.8% |
| ARC-AGI-2 | — | 0.8% |
| Chess Puzzles | 15% | — |
| EnigmaEval | 5.7% | — |
| DTBench | 74.7% | — |
| LMCA | 22.3% | — |

## Math

- o1: 36.1 (#175)
- o1-mini: 35.4 (#186)

| Benchmark | o1 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 46.9% |
| LiveBench Math | 80.3% | 62% |
| LMArena Math | 1388 | 1358 |
| MATH Level 5 | 94.7% | 89.2% |
| FrontierMath (Feb 2025 set) | 9.3% | 1.7% |
| FrontierMath (Tiers 1-3) | 14.7% | — |

## Knowledge

- o1: 41.5 (#110)
- o1-mini: 34.9 (#192)

| Benchmark | o1 | o1-mini |
|---|---|---|
| GPQA Diamond | 76.8% | 62.4% |
| Confabulations | 11.7% | 18.6% |
| LMArena Expert | 1361 | 1316 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |

## Multimodal

- o1: 34.2 (#93)
- o1-mini: —

| Benchmark | o1 | o1-mini |
|---|---|---|
| LMArena Vision | 1168 | — |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |

## Multilingual

- o1: 48.6 (#142)
- o1-mini: 43.6 (#182)

| Benchmark | o1 | o1-mini |
|---|---|---|
| LMArena Non-English | 1358 | 1289 |
| LMArena Chinese | 1394 | 1314 |
| LMArena French | 1344 | 1293 |
| LMArena German | 1337 | 1278 |
| LMArena Japanese | 1346 | 1245 |
| LMArena Korean | 1396 | 1223 |
| LMArena Russian | 1356 | 1283 |
| LMArena Spanish | 1345 | 1303 |

## Instruction Following

- o1: 74.8 (#86)
- o1-mini: 66.7 (#206)

| Benchmark | o1 | o1-mini |
|---|---|---|
| LiveBench Instruction Following | 81.5% | 65.4% |
| LMArena Instruction Following | 1367 | 1304 |

## Long Context

- o1: 50.3 (#9)
- o1-mini: 40.1 (#161)

| Benchmark | o1 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1378 | 1320 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- o1: 55.6 (#144)
- o1-mini: 48.4 (#202)

| Benchmark | o1 | o1-mini |
|---|---|---|
| LMArena Text | 1366 | 1317 |
| LMArena Creative Writing | 1348 | 1244 |
| Short-Story Creative Writing | 70.2% | 64.9% |
| LMArena Multi-Turn | 1369 | 1314 |
| LiveBench Language | 65.4% | 40.9% |

## FAQ

### Is o1 better than o1-mini?

o1 is the stronger model overall, scoring 40.9 to 34.0 on the Noometry Index.

### Is o1 or o1-mini better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 35.5 in the Noometry coding category.

### How many benchmarks do o1 and o1-mini share?

38 benchmarks have published results for both models. o1 has 52 scored results on Noometry and o1-mini has 39.