# GPT-4 vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GPT-4 scores higher in 0 categories and MiniMax-M2.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 58.9 to 34.9.
- The biggest single-benchmark swing is WeirdML: 12.4% for GPT-4 and 37% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $30 / $60 for GPT-4.
- MiniMax-M2.7 accepts more context: 205K tokens versus 8K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 29.1 | 37.7 |
| Rank | 316 | 196 |
| Context | 8K | 205K |
| Input $/M | $30 | $0.30 |
| Output $/M | $60 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-4: 31.6 (#283)
- MiniMax-M2.7: 41.8 (#120)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| WeirdML | 12.4% | 37% |
| LMArena Coding | 1254 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 599.25 |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- MiniMax-M2.7: 25.1 (#111)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.8 (#289)
- MiniMax-M2.7: 19.7 (#253)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1422 |
| Epoch Capabilities Index | 125.89 | 145.85 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | 4% | — |
| Thematic Generalization | — | 39.3% |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.8 (#309)
- MiniMax-M2.7: 25.9 (#263)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1269 | 1420 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| ProofBench | — | 3% |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#282)
- MiniMax-M2.7: 37.7 (#152)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1211 | 1444 |
| GPQA Diamond | 35.7% | — |
| Vectara Hallucination Rate | — | 12.9% |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multilingual

- GPT-4: 40.6 (#215)
- MiniMax-M2.7: 50.3 (#123)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1246 | 1382 |
| LMArena Chinese | 1242 | 1441 |
| LMArena French | 1283 | 1421 |
| LMArena German | 1251 | 1398 |
| LMArena Japanese | 1209 | 1262 |
| LMArena Korean | 1184 | 1313 |
| LMArena Russian | 1251 | 1383 |
| LMArena Spanish | 1261 | 1403 |

## Instruction Following

- GPT-4: 65.3 (#222)
- MiniMax-M2.7: 74.1 (#103)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1405 |

## Long Context

- GPT-4: 37.7 (#212)
- MiniMax-M2.7: 43.3 (#99)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1244 | 1419 |

## Writing & Preference

- GPT-4: 34.9 (#268)
- MiniMax-M2.7: 58.9 (#112)

| Benchmark | GPT-4 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1263 | 1405 |
| LMArena Creative Writing | 1244 | 1354 |
| LMArena Multi-Turn | 1257 | 1412 |
| EQ-Bench Creative Writing | 752 | — |

## FAQ

### Is GPT-4 better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 29.1 on the Noometry Index.

### Which is cheaper, GPT-4 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-4 lists at $30 and $60.

### Is GPT-4 or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 8K.

### How many benchmarks do GPT-4 and MiniMax-M2.7 share?

19 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and MiniMax-M2.7 has 30.