# GPT-4.1 mini vs GPT-4o mini

> GPT-4.1 mini is the stronger model overall, scoring 33.5 to 25.4 on the Noometry Index. GPT-4o mini costs 2.7× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4-1-mini-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. GPT-4.1 mini scores higher in 9 categories and GPT-4o mini in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 mini leads 34.7 to 17.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.5 | 25.4 |
| Rank | 232 | 337 |
| Context | 1.05M | 128K |
| Input $/M | $0.40 | $0.15 |
| Output $/M | $1.60 | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1 mini: 30.4 (#286)
- GPT-4o mini: 21.6 (#330)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| Aider Polyglot | 32.4% | 3.6% |
| WeirdML | 37.6% | 11.8% |
| BigCodeBench Instruct | 48.9% | 46.1% |
| LMArena Coding | 1367 | 1290 |
| SWE-bench Verified (bash only) | 23.9% | — |
| SciCode | 40.4% | — |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| CadEval | 16% | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- GPT-4.1 mini: 33.0 (#52)
- GPT-4o mini: 27.2 (#95)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
| BALROG | — | 17.4% |

## Reasoning

- GPT-4.1 mini: 10.9 (#335)
- GPT-4o mini: 8.7 (#343)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0% |
| Kagi LLM Benchmark | 48.6% | 28.8% |
| Chess Puzzles | 7% | 0% |
| LMArena Hard Prompts | 1349 | 1267 |
| Mystery Game Puzzles | 7% | 12% |
| DTBench | 68.8% | 54.4% |
| LMCA | 21.1% | 10.4% |
| Epoch Capabilities Index | 135.01 | 126.56 |
| SimpleBench | — | 10.7% |
| ARC-AGI-1 | 3.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 32.8% |
| LiveBench Data Analysis | — | 50% |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- GPT-4.1 mini: 23.1 (#264)
- GPT-4o mini: 9.9 (#307)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 0.7% |
| OTIS Mock AIME 2024-2025 | 44.7% | 6.9% |
| Omni-MATH | 49.1% | 28% |
| LMArena Math | 1343 | 1267 |
| MATH Level 5 | 87.3% | 52.6% |
| LiveBench Math | — | 36.3% |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| GSM8K | — | 91.3% |

## Knowledge

- GPT-4.1 mini: 34.7 (#183)
- GPT-4o mini: 17.7 (#279)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 65.8% | 37.7% |
| SimpleQA Verified | 12.7% | 8.3% |
| MMLU-Pro | 78.3% | 60.3% |
| GPQA (HELM) | 61.4% | 36.8% |
| LMArena Expert | 1338 | 1235 |
| Confabulations | — | 37.2% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- GPT-4.1 mini: 35.2 (#77)
- GPT-4o mini: 25.3 (#117)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1181 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |

## Multilingual

- GPT-4.1 mini: 45.9 (#161)
- GPT-4o mini: 42.2 (#194)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1318 | 1266 |
| LMArena Chinese | 1329 | 1264 |
| LMArena French | 1357 | 1296 |
| LMArena German | 1349 | 1272 |
| LMArena Japanese | 1291 | 1216 |
| LMArena Korean | 1298 | 1195 |
| LMArena Russian | 1324 | 1275 |
| LMArena Spanish | 1319 | 1276 |

## Instruction Following

- GPT-4.1 mini: 73.9 (#113)
- GPT-4o mini: 62.1 (#234)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| IFEval | 90.4% | 78.2% |
| LMArena Instruction Following | 1332 | 1259 |
| LiveBench Instruction Following | — | 56.8% |

## Long Context

- GPT-4.1 mini: 31.8 (#270)
- GPT-4o mini: 39.1 (#181)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1344 | 1289 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-4.1 mini: 48.8 (#193)
- GPT-4o mini: 39.7 (#243)

| Benchmark | GPT-4.1 mini | GPT-4o mini |
|---|---|---|
| LMArena Text | 1341 | 1286 |
| LMArena Creative Writing | 1300 | 1268 |
| EQ-Bench Creative Writing | 1147 | 873 |
| WildBench | 83.8% | 79.1% |
| LMArena Multi-Turn | 1354 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| LiveBench Language | — | 28.6% |

## FAQ

### Is GPT-4.1 mini better than GPT-4o mini?

GPT-4.1 mini is the stronger model overall, scoring 33.5 to 25.4 on the Noometry Index. GPT-4o mini costs 2.7× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.

### Which is cheaper, GPT-4.1 mini or GPT-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

### Is GPT-4.1 mini or GPT-4o mini better for coding?

GPT-4.1 mini scores higher on coding benchmarks: 30.4 versus 21.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 128K.

### How many benchmarks do GPT-4.1 mini and GPT-4o mini share?

39 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-4o mini has 60.