# GPT-6.1 Sol vs MiniMax-M3

> GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 43.8 on the Noometry Index. MiniMax-M3 costs 7.6× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-6-1-sol-vs-minimax-m3
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GPT-6.1 Sol scores higher in 10 categories and MiniMax-M3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 40.0.
- The biggest single-benchmark swing is ProofBench: 99% for GPT-6.1 Sol and 18% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 1M.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 65.6 | 43.8 |
| Rank | 6 | 85 |
| Context | 1.05M | 1M |
| Input $/M | $2 | $0.30 |
| Output $/M | $10 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-6.1 Sol: 63.2 (#8)
- MiniMax-M3: 41.8 (#118)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| FrontierCode | 50.2% | 14.7% |
| LMArena WebDev | 1755 | 1482 |
| SciCode | 55.8% | 47.1% |
| LMArena Coding | 1487 | 1469 |
| DeepSWE | 75.2% | — |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- GPT-6.1 Sol: 39.6 (#26)
- MiniMax-M3: 22.6 (#130)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 60% | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| GDP.pdf | 32% | — |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- GPT-6.1 Sol: 81.9 (#2)
- MiniMax-M3: 30.1 (#87)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| NYT Connections (extended) | 95.5% | 65.1% |
| CritPt | 31.7% | 3.7% |
| Chess Puzzles | 61% | 14% |
| LMArena Hard Prompts | 1466 | 1447 |
| Mystery Game Puzzles | 80% | 8% |
| Epoch Capabilities Index | 166.09 | 146.95 |
| ARC-AGI-2 | 94.2% | — |
| SimpleBench | — | 45.8% |
| ARC-AGI-1 | 98.5% | — |
| EBR-Bench | 54.3% | — |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |

## Math

- GPT-6.1 Sol: 93.7 (#1)
- MiniMax-M3: 40.0 (#95)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 71.1% |
| ProofBench | 99% | 18% |
| LMArena Math | 1464 | 1429 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |

## Knowledge

- GPT-6.1 Sol: 71.8 (#4)
- MiniMax-M3: 58.4 (#35)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 95.4% | 90.9% |
| LMArena Expert | 1502 | 1461 |
| SimpleQA Verified | 73.9% | — |

## Multimodal

- GPT-6.1 Sol: 52.7 (#5)
- MiniMax-M3: 40.2 (#51)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1288 | 1253 |
| Furniture Assembly | 80% | — |
| LMArena Document | — | 1435 |

## Multilingual

- GPT-6.1 Sol: 54.3 (#46)
- MiniMax-M3: 53.0 (#75)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1438 | 1420 |
| LMArena Chinese | 1477 | 1463 |
| LMArena Russian | 1455 | 1428 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Spanish | — | 1432 |

## Instruction Following

- GPT-6.1 Sol: 77.0 (#29)
- MiniMax-M3: 75.5 (#62)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1468 | 1433 |

## Long Context

- GPT-6.1 Sol: 44.9 (#54)
- MiniMax-M3: 44.2 (#72)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1465 | 1445 |

## Writing & Preference

- GPT-6.1 Sol: 63.6 (#63)
- MiniMax-M3: 62.1 (#83)

| Benchmark | GPT-6.1 Sol | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1447 | 1433 |
| LMArena Creative Writing | 1432 | 1404 |
| LMArena Multi-Turn | 1449 | 1442 |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is GPT-6.1 Sol better than MiniMax-M3?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 43.8 on the Noometry Index. MiniMax-M3 costs 7.6× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

### Which is cheaper, GPT-6.1 Sol or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

### Is GPT-6.1 Sol or MiniMax-M3 better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 1M.

### How many benchmarks do GPT-6.1 Sol and MiniMax-M3 share?

25 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and MiniMax-M3 has 41.