# GPT-4 Turbo vs o1-mini

> o1-mini is the stronger model overall, scoring 33.7 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-turbo-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and o1-mini in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 33.7 to 8.6.
- The biggest single-benchmark swing is MATH Level 5: 46.7% for GPT-4 Turbo and 89.2% for o1-mini.

## Snapshot

| | GPT-4 Turbo | o1-mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.3 | 33.7 |
| Rank | 281 | 230 |
| Context | 128K | — |
| Input $/M | $10 | — |
| Output $/M | $30 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4 Turbo: 33.4 (#247)
- o1-mini: 35.1 (#218)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| WeirdML | 18% | 36.3% |
| LMArena Coding | 1268 | 1362 |
| HumanEval+ | 86.6% | 89% |
| MBPP+ | 73.3% | 78.8% |
| Aider Polyglot | — | 32.9% |
| BigCodeBench Instruct | 48.2% | — |
| LiveBench Coding | — | 48% |
| BigCodeBench Complete | 58.2% | — |

## Agentic & Tool Use

- GPT-4 Turbo: —
- o1-mini: 24.3 (#112)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | 36.7% | — |

## Reasoning

- GPT-4 Turbo: 14.9 (#311)
- o1-mini: 8.9 (#340)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| SimpleBench | 25.1% | 18.1% |
| LMArena Hard Prompts | 1251 | 1333 |
| Epoch Capabilities Index | 127.25 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| ARC-AGI-1 | — | 14% |
| Chess Puzzles | 6% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 9.8% | — |
| ForecastBench | 59.4 | — |
| LiveBench | — | 57.8% |

## Math

- GPT-4 Turbo: 8.6 (#316)
- o1-mini: 33.7 (#168)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 46.9% |
| LMArena Math | 1272 | 1358 |
| MATH Level 5 | 46.7% | 89.2% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| LiveBench Math | — | 62% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- GPT-4 Turbo: 24.3 (#263)
- o1-mini: 34.8 (#180)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| GPQA Diamond | 46.6% | 62.4% |
| Confabulations | 28.4% | 18.6% |
| LMArena Expert | 1223 | 1316 |
| MMLU | 81.3% | — |

## Multimodal

- GPT-4 Turbo: 30.0 (#104)
- o1-mini: —

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| LMArena Vision | 1090 | — |

## Multilingual

- GPT-4 Turbo: 40.7 (#211)
- o1-mini: 43.8 (#177)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| LMArena Non-English | 1245 | 1289 |
| LMArena Chinese | 1242 | 1314 |
| LMArena French | 1275 | 1292 |
| LMArena German | 1259 | 1278 |
| LMArena Japanese | 1194 | 1245 |
| LMArena Korean | 1187 | 1223 |
| LMArena Russian | 1259 | 1283 |
| LMArena Spanish | 1260 | 1302 |

## Instruction Following

- GPT-4 Turbo: 66.0 (#211)
- o1-mini: 67.0 (#200)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1250 | 1304 |
| LiveBench Instruction Following | — | 65.4% |

## Long Context

- GPT-4 Turbo: 38.0 (#200)
- o1-mini: 40.1 (#156)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| LMArena Longer Query | 1254 | 1321 |

## Writing & Preference

- GPT-4 Turbo: 47.9 (#201)
- o1-mini: 48.6 (#196)

| Benchmark | GPT-4 Turbo | o1-mini |
|---|---|---|
| LMArena Text | 1272 | 1317 |
| LMArena Creative Writing | 1269 | 1244 |
| LMArena Multi-Turn | 1267 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| LiveBench Language | — | 40.9% |

## FAQ

### Is GPT-4 Turbo better than o1-mini?

o1-mini is the stronger model overall, scoring 33.7 to 30.3 on the Noometry Index.

### Is GPT-4 Turbo or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.1 versus 33.4 in the Noometry coding category.

### How many benchmarks do GPT-4 Turbo and o1-mini share?

26 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and o1-mini has 39.