# GPT-4.1 mini vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.5 to 33.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-mini-vs-minimax-m3
- 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 1 category and MiniMax-M3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 34.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 71.1% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 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 1M.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 33.5 | 43.5 |
| Rank | 232 | 81 |
| Context | 1.05M | 1M |
| Input $/M | $0.40 | $0.30 |
| Output $/M | $1.60 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.1 mini: 30.4 (#286)
- MiniMax-M3: 41.5 (#111)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| SciCode | 40.4% | 47.1% |
| LMArena Coding | 1367 | 1470 |
| FrontierCode | — | 14.7% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1482 |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- GPT-4.1 mini: 33.0 (#52)
- MiniMax-M3: 22.5 (#121)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| Berkeley Function Calling Leaderboard | 50.5% | — |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- GPT-4.1 mini: 10.9 (#335)
- MiniMax-M3: 29.3 (#83)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| CritPt | 0% | 3.7% |
| Chess Puzzles | 7% | 14% |
| LMArena Hard Prompts | 1349 | 1447 |
| Mystery Game Puzzles | 7% | 8% |
| DTBench | 68.8% | 78.9% |
| LMCA | 21.1% | 33.7% |
| Epoch Capabilities Index | 135.01 | 147 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | 48.6% | — |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 3.5% | — |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |

## Math

- GPT-4.1 mini: 23.1 (#264)
- MiniMax-M3: 39.1 (#83)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.7% | 71.1% |
| LMArena Math | 1343 | 1432 |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| ProofBench | — | 18% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |

## Knowledge

- GPT-4.1 mini: 34.7 (#183)
- MiniMax-M3: 58.4 (#32)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 65.8% | 90.9% |
| LMArena Expert | 1338 | 1462 |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |

## Multimodal

- GPT-4.1 mini: 35.2 (#77)
- MiniMax-M3: 39.5 (#45)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1181 | 1254 |
| LMArena Document | — | 1435 |

## Multilingual

- GPT-4.1 mini: 45.9 (#161)
- MiniMax-M3: 53.2 (#70)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1318 | 1420 |
| LMArena Chinese | 1329 | 1465 |
| LMArena French | 1357 | 1445 |
| LMArena German | 1349 | 1424 |
| LMArena Japanese | 1291 | 1381 |
| LMArena Korean | 1298 | 1372 |
| LMArena Russian | 1324 | 1430 |
| LMArena Spanish | 1319 | 1431 |

## Instruction Following

- GPT-4.1 mini: 73.9 (#113)
- MiniMax-M3: 75.7 (#56)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1332 | 1433 |
| IFEval | 90.4% | — |

## Long Context

- GPT-4.1 mini: 31.8 (#270)
- MiniMax-M3: 44.2 (#68)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1344 | 1445 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-4.1 mini: 48.8 (#193)
- MiniMax-M3: 62.3 (#79)

| Benchmark | GPT-4.1 mini | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1341 | 1433 |
| LMArena Creative Writing | 1300 | 1405 |
| LMArena Multi-Turn | 1354 | 1441 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is GPT-4.1 mini better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 33.5 on the Noometry Index.

### Which is cheaper, GPT-4.1 mini or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

### Is GPT-4.1 mini or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 30.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 1M.

### How many benchmarks do GPT-4.1 mini and MiniMax-M3 share?

27 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and MiniMax-M3 has 41.