# GPT-4.5 vs o1-mini

> GPT-4.5 is the stronger model overall, scoring 36.9 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. GPT-4.5 scores higher in 7 categories and o1-mini in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4.5 leads 52.7 to 43.8.
- The biggest single-benchmark swing is LiveBench Coding: 75.2% for GPT-4.5 and 48% for o1-mini.

## Snapshot

| | GPT-4.5 | o1-mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 36.9 | 33.7 |
| Rank | 200 | 230 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.5: 41.8 (#102)
- o1-mini: 35.1 (#218)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| Aider Polyglot | 44.9% | 32.9% |
| WeirdML | 39.4% | 36.3% |
| LiveBench Coding | 75.2% | 48% |
| LMArena Coding | 1397 | 1362 |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |

## Agentic & Tool Use

- GPT-4.5: 27.6 (#92)
- o1-mini: 24.3 (#112)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| Cybench | 17.5% | 10% |

## Reasoning

- GPT-4.5: 14.1 (#320)
- o1-mini: 8.9 (#340)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0.8% |
| SimpleBench | 34.5% | 18.1% |
| ARC-AGI-1 | 10.3% | 14% |
| LiveBench Reasoning | 71.1% | 72.3% |
| LMArena Hard Prompts | 1404 | 1333 |
| LiveBench Data Analysis | 64.3% | 57.9% |
| Epoch Capabilities Index | 136.74 | 135.82 |
| LiveBench | 69% | 57.8% |
| EnigmaEval | 3.2% | — |
| ForecastBench | 61.7 | — |

## Math

- GPT-4.5: 31.0 (#200)
- o1-mini: 33.7 (#168)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 46.9% |
| LiveBench Math | 69.3% | 62% |
| LMArena Math | 1412 | 1358 |
| MATH Level 5 | 78.6% | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- GPT-4.5: 32.4 (#205)
- o1-mini: 34.8 (#180)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| GPQA Diamond | 68.7% | 62.4% |
| Confabulations | 13.6% | 18.6% |
| LMArena Expert | 1394 | 1316 |
| Humanity's Last Exam | 5.4% | — |

## Multimodal

- GPT-4.5: 37.0 (#68)
- o1-mini: —

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.7 (#78)
- o1-mini: 43.8 (#177)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| LMArena Non-English | 1413 | 1289 |
| LMArena Chinese | 1421 | 1314 |
| LMArena French | 1417 | 1292 |
| LMArena German | 1457 | 1278 |
| LMArena Japanese | 1416 | 1245 |
| LMArena Korean | 1392 | 1223 |
| LMArena Russian | 1419 | 1283 |
| LMArena Spanish | — | 1302 |

## Instruction Following

- GPT-4.5: 72.8 (#129)
- o1-mini: 67.0 (#200)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| LiveBench Instruction Following | 72.3% | 65.4% |
| LMArena Instruction Following | 1404 | 1304 |

## Long Context

- GPT-4.5: 40.4 (#150)
- o1-mini: 40.1 (#156)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1406 | 1321 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 57.1 (#129)
- o1-mini: 48.6 (#196)

| Benchmark | GPT-4.5 | o1-mini |
|---|---|---|
| LMArena Text | 1417 | 1317 |
| LMArena Creative Writing | 1394 | 1244 |
| Short-Story Creative Writing | 75.6% | 64.9% |
| LMArena Multi-Turn | 1444 | 1314 |
| LiveBench Language | 61.5% | 40.9% |
| EQ-Bench Creative Writing | 1258 | — |

## FAQ

### Is GPT-4.5 better than o1-mini?

GPT-4.5 is the stronger model overall, scoring 36.9 to 33.7 on the Noometry Index.

### Is GPT-4.5 or o1-mini better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 35.1 in the Noometry coding category.

### How many benchmarks do GPT-4.5 and o1-mini share?

35 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and o1-mini has 39.