# MiniMax-M2.7 vs Qwen3.6 Plus

> Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 2.1× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-qwen3-6-plus
- Last updated: 2026-10-12
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. MiniMax-M2.7 scores higher in 1 category and Qwen3.6 Plus in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 25.9.
- The biggest single-benchmark swing is NYT Connections (extended): 24.7% for MiniMax-M2.7 and 60.3% for Qwen3.6 Plus.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 47.5 |
| Rank | 196 | 62 |
| Context | 205K | 1M |
| Input $/M | $0.30 | $0.50 |
| Output $/M | $1.20 | $3 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2.7: 41.8 (#120)
- Qwen3.6 Plus: 40.8 (#130)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1398 | 1461 |
| SciCode | 47% | 40.7% |
| LMArena Coding | 1454 | 1467 |
| ALE-Bench | 599.25 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| WeirdML | 37% | — |

## Agentic & Tool Use

- MiniMax-M2.7: 25.1 (#111)
- Qwen3.6 Plus: —

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | — | 5,115 |

## Reasoning

- MiniMax-M2.7: 19.7 (#253)
- Qwen3.6 Plus: 29.3 (#93)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 24.7% | 60.3% |
| CritPt | 0.6% | 2.9% |
| Thematic Generalization | 39.3% | 59.5% |
| LMArena Hard Prompts | 1422 | 1449 |
| Epoch Capabilities Index | 145.85 | 147.65 |
| Chess Puzzles | — | 17% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |

## Math

- MiniMax-M2.7: 25.9 (#263)
- Qwen3.6 Plus: 51.8 (#54)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1420 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | 3% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |

## Knowledge

- MiniMax-M2.7: 37.7 (#152)
- Qwen3.6 Plus: 56.1 (#45)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1444 | 1454 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
| Vectara Hallucination Rate | 12.9% | — |

## Multilingual

- MiniMax-M2.7: 50.3 (#123)
- Qwen3.6 Plus: 53.3 (#70)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1382 | 1424 |
| LMArena Chinese | 1441 | 1477 |
| LMArena French | 1421 | 1455 |
| LMArena German | 1398 | 1452 |
| LMArena Japanese | 1262 | 1389 |
| LMArena Korean | 1313 | 1379 |
| LMArena Russian | 1383 | 1434 |
| LMArena Spanish | 1403 | 1432 |

## Instruction Following

- MiniMax-M2.7: 74.1 (#103)
- Qwen3.6 Plus: 75.0 (#74)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1405 | 1425 |

## Long Context

- MiniMax-M2.7: 43.3 (#99)
- Qwen3.6 Plus: 45.2 (#49)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1419 | 1439 |
| CL-bench | — | 20.3% |

## Writing & Preference

- MiniMax-M2.7: 58.9 (#112)
- Qwen3.6 Plus: 62.2 (#82)

| Benchmark | MiniMax-M2.7 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1405 | 1437 |
| LMArena Creative Writing | 1354 | 1404 |
| LMArena Multi-Turn | 1412 | 1438 |

## FAQ

### Is MiniMax-M2.7 better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 2.1× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.

### Which is cheaper, MiniMax-M2.7 or Qwen3.6 Plus?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.

### Is MiniMax-M2.7 or Qwen3.6 Plus better for coding?

They score almost the same on coding (41.8 vs 40.8); test both on your own repository before choosing.

### Which has the bigger context window?

Qwen3.6 Plus does, with 1M tokens against 205K.

### How many benchmarks do MiniMax-M2.7 and Qwen3.6 Plus share?

24 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3.6 Plus has 37.