# GPT-4.1 mini vs GPT-4.5

> GPT-4.5 is the stronger model overall, scoring 36.9 to 33.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-mini-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. GPT-4.1 mini scores higher in 3 categories and GPT-4.5 in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-4.5 leads 41.8 to 30.4.
- The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for GPT-4.1 mini and 63.9% for GPT-4.5.

## Snapshot

| | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.5 | 36.9 |
| Rank | 232 | 200 |
| Context | 1.05M | — |
| Input $/M | $0.40 | — |
| Output $/M | $1.60 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1 mini: 30.4 (#286)
- GPT-4.5: 41.8 (#102)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| Aider Polyglot | 32.4% | 44.9% |
| WeirdML | 37.6% | 39.4% |
| LMArena Coding | 1367 | 1397 |
| SWE-bench Verified (bash only) | 23.9% | — |
| SciCode | 40.4% | — |
| BigCodeBench Instruct | 48.9% | — |
| LiveBench Coding | — | 75.2% |
| CadEval | 16% | — |

## Agentic & Tool Use

- GPT-4.1 mini: 33.0 (#52)
- GPT-4.5: 27.6 (#92)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
| Cybench | — | 17.5% |

## Reasoning

- GPT-4.1 mini: 10.9 (#335)
- GPT-4.5: 14.1 (#320)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | 0% | 0.8% |
| ARC-AGI-1 | 3.5% | 10.3% |
| LMArena Hard Prompts | 1349 | 1404 |
| Epoch Capabilities Index | 135.01 | 136.74 |
| SimpleBench | — | 34.5% |
| Kagi LLM Benchmark | 48.6% | — |
| CritPt | 0% | — |
| Chess Puzzles | 7% | — |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LiveBench Data Analysis | — | 64.3% |
| LMCA | 21.1% | — |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |

## Math

- GPT-4.1 mini: 23.1 (#264)
- GPT-4.5: 31.0 (#200)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 37.8% |
| LMArena Math | 1343 | 1412 |
| MATH Level 5 | 87.3% | 78.6% |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| Omni-MATH | 49.1% | — |
| LiveBench Math | — | 69.3% |
| FrontierMath (Feb 2025 set) | 4.5% | — |

## Knowledge

- GPT-4.1 mini: 34.7 (#183)
- GPT-4.5: 32.4 (#205)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 65.8% | 68.7% |
| LMArena Expert | 1338 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| Confabulations | — | 13.6% |
| GPQA (HELM) | 61.4% | — |

## Multimodal

- GPT-4.1 mini: 35.2 (#77)
- GPT-4.5: 37.0 (#68)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1181 | 1195 |
| VPCT | — | 45% |

## Multilingual

- GPT-4.1 mini: 45.9 (#161)
- GPT-4.5: 52.7 (#78)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1318 | 1413 |
| LMArena Chinese | 1329 | 1421 |
| LMArena French | 1357 | 1417 |
| LMArena German | 1349 | 1457 |
| LMArena Japanese | 1291 | 1416 |
| LMArena Korean | 1298 | 1392 |
| LMArena Russian | 1324 | 1419 |
| LMArena Spanish | 1319 | — |

## Instruction Following

- GPT-4.1 mini: 73.9 (#113)
- GPT-4.5: 72.8 (#129)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1332 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
| IFEval | 90.4% | — |

## Long Context

- GPT-4.1 mini: 31.8 (#270)
- GPT-4.5: 40.4 (#150)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| Fiction.LiveBench | 44.4% | 63.9% |
| LMArena Longer Query | 1344 | 1406 |

## Writing & Preference

- GPT-4.1 mini: 48.8 (#193)
- GPT-4.5: 57.1 (#129)

| Benchmark | GPT-4.1 mini | GPT-4.5 |
|---|---|---|
| LMArena Text | 1341 | 1417 |
| LMArena Creative Writing | 1300 | 1394 |
| EQ-Bench Creative Writing | 1147 | 1258 |
| LMArena Multi-Turn | 1354 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| WildBench | 83.8% | — |
| LiveBench Language | — | 61.5% |

## FAQ

### Is GPT-4.1 mini better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 36.9 to 33.5 on the Noometry Index.

### Is GPT-4.1 mini or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 30.4 in the Noometry coding category.

### How many benchmarks do GPT-4.1 mini and GPT-4.5 share?

27 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-4.5 has 42.