# GPT-6 Sol vs MiniMax-M2

> GPT-6 Sol is the stronger model overall, scoring 49.2 to 36.9 on the Noometry Index. MiniMax-M2 costs 7.6× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-6-sol-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and MiniMax-M2 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 18.6.
- The biggest single-benchmark swing is NYT Connections (extended): 90.1% for GPT-6 Sol and 14.8% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 49.2 | 36.9 |
| Rank | 46 | 201 |
| Context | 1.05M | 205K |
| Input $/M | $2 | $0.30 |
| Output $/M | $10 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-6 Sol: 59.6 (#11)
- MiniMax-M2: 39.1 (#151)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1692 | 1297 |
| LMArena Coding | 1453 | 1370 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| SWE-bench Verified (bash only) | — | 61% |

## Agentic & Tool Use

- GPT-6 Sol: 33.5 (#49)
- MiniMax-M2: 24.9 (#102)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| GDP.pdf | 28% | — |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- GPT-6 Sol: 49.3 (#34)
- MiniMax-M2: 18.6 (#256)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| NYT Connections (extended) | 90.1% | 14.8% |
| LMArena Hard Prompts | 1420 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| EBR-Bench | 53.3% | — |

## Math

- GPT-6 Sol: 35.8 (#135)
- MiniMax-M2: 34.6 (#158)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1404 | 1350 |

## Knowledge

- GPT-6 Sol: 43.0 (#87)
- MiniMax-M2: 36.3 (#160)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1449 | 1336 |
| Vectara Hallucination Rate | 6.5% | — |

## Multimodal

- GPT-6 Sol: 47.6 (#9)
- MiniMax-M2: —

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| Furniture Assembly | 58.3% | — |

## Multilingual

- GPT-6 Sol: 51.0 (#113)
- MiniMax-M2: 45.6 (#165)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1389 | 1314 |
| LMArena Chinese | 1416 | 1367 |
| LMArena Russian | 1407 | 1332 |
| LMArena Spanish | 1377 | 1326 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |

## Instruction Following

- GPT-6 Sol: 74.4 (#97)
- MiniMax-M2: 70.4 (#160)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1329 |

## Long Context

- GPT-6 Sol: 43.2 (#100)
- MiniMax-M2: 40.5 (#148)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1415 | 1332 |

## Writing & Preference

- GPT-6 Sol: 72.3 (#15)
- MiniMax-M2: 53.3 (#157)

| Benchmark | GPT-6 Sol | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1396 | 1340 |
| LMArena Creative Writing | 1392 | 1288 |
| LMArena Multi-Turn | 1405 | 1362 |
| EQ-Bench Creative Writing | 2125 | — |

## FAQ

### Is GPT-6 Sol better than MiniMax-M2?

GPT-6 Sol is the stronger model overall, scoring 49.2 to 36.9 on the Noometry Index. MiniMax-M2 costs 7.6× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.

### Which is cheaper, GPT-6 Sol or MiniMax-M2?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-6 Sol lists at $2 and $10.

### Is GPT-6 Sol or MiniMax-M2 better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Sol does, with 1.05M tokens against 205K.

### How many benchmarks do GPT-6 Sol and MiniMax-M2 share?

15 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and MiniMax-M2 has 21.