# GPT-5.4 mini vs MiniMax-M2.1

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 3.2× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-minimax-m2-1
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and MiniMax-M2.1 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 mini leads 30.3 to 15.8.
- The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 11.2% for MiniMax-M2.1.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 205K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 44.8 | 38.4 |
| Rank | 69 | 177 |
| Context | 400K | 205K |
| Input $/M | $0.75 | $0.30 |
| Output $/M | $4.50 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.0 (#67)
- MiniMax-M2.1: 40.1 (#132)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | 1397 | 1384 |
| LMArena Coding | 1438 | 1421 |
| ALE-Bench | 1,189 | 623.83 |
| FrontierCode | 27% | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.6 (#74)
- MiniMax-M2.1: 27.7 (#91)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.3 (#77)
- MiniMax-M2.1: 15.8 (#301)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| NYT Connections (extended) | 61.8% | 11.2% |
| LMArena Hard Prompts | 1424 | 1410 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.83 | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.4 (#63)
- MiniMax-M2.1: 35.6 (#142)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1418 | 1396 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.4 (#62)
- MiniMax-M2.1: 37.7 (#143)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 11.8% |
| LMArena Expert | 1434 | 1432 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |

## Multimodal

- GPT-5.4 mini: 39.0 (#51)
- MiniMax-M2.1: —

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 52.1 (#94)
- MiniMax-M2.1: 50.2 (#123)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1405 | 1378 |
| LMArena Chinese | 1446 | 1430 |
| LMArena French | 1440 | 1405 |
| LMArena German | 1407 | 1380 |
| LMArena Japanese | 1375 | 1287 |
| LMArena Korean | 1369 | 1297 |
| LMArena Russian | 1417 | 1386 |
| LMArena Spanish | 1403 | 1396 |

## Instruction Following

- GPT-5.4 mini: 74.3 (#99)
- MiniMax-M2.1: 74.0 (#108)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1399 |

## Long Context

- GPT-5.4 mini: 42.9 (#107)
- MiniMax-M2.1: 43.2 (#98)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1407 | 1416 |

## Writing & Preference

- GPT-5.4 mini: 64.2 (#56)
- MiniMax-M2.1: 58.5 (#114)

| Benchmark | GPT-5.4 mini | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1411 | 1392 |
| LMArena Creative Writing | 1370 | 1362 |
| LMArena Multi-Turn | 1429 | 1396 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than MiniMax-M2.1?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 3.2× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.4 mini or MiniMax-M2.1?

MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

### Is GPT-5.4 mini or MiniMax-M2.1 better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 205K.

### How many benchmarks do GPT-5.4 mini and MiniMax-M2.1 share?

21 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and MiniMax-M2.1 has 22.