# MiniMax-M3 vs Qwen3.6 Plus

> Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 43.5 on the Noometry Index. MiniMax-M3 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-m3-vs-qwen3-6-plus
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. MiniMax-M3 scores higher in 4 categories and Qwen3.6 Plus in 4 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 50.6 to 39.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for MiniMax-M3 and 93.3% for Qwen3.6 Plus.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.5 | 47.3 |
| Rank | 81 | 54 |
| Context | 1M | 1M |
| Input $/M | $0.30 | $0.50 |
| Output $/M | $1.20 | $3 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M3: 41.5 (#111)
- Qwen3.6 Plus: 40.6 (#125)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1482 | 1461 |
| SciCode | 47.1% | 40.7% |
| LMArena Coding | 1470 | 1467 |
| ALE-Bench | 640.02 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| FrontierCode | 14.7% | — |

## Agentic & Tool Use

- MiniMax-M3: 22.5 (#121)
- Qwen3.6 Plus: —

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 2,158 | 5,115 |
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |

## Reasoning

- MiniMax-M3: 29.3 (#83)
- Qwen3.6 Plus: 28.5 (#89)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 65.1% | 60.3% |
| CritPt | 3.7% | 2.9% |
| Chess Puzzles | 14% | 17% |
| LMArena Hard Prompts | 1447 | 1449 |
| Mystery Game Puzzles | 8% | 12% |
| DTBench | 78.9% | 81.9% |
| LMCA | 33.7% | 33.1% |
| Epoch Capabilities Index | 147 | 147.67 |
| SimpleBench | 45.8% | — |
| Thematic Generalization | — | 59.5% |
| Surface Evolver Bench | 55% | — |
| ForecastBench | 61.4 | — |

## Math

- MiniMax-M3: 39.1 (#83)
- Qwen3.6 Plus: 50.6 (#44)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 93.3% |
| LMArena Math | 1432 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| ProofBench | 18% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |

## Knowledge

- MiniMax-M3: 58.4 (#32)
- Qwen3.6 Plus: 56.1 (#40)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 90.9% | 88.4% |
| LMArena Expert | 1462 | 1456 |
| SimpleQA Verified | — | 44.1% |

## Multimodal

- MiniMax-M3: 39.5 (#45)
- Qwen3.6 Plus: —

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1254 | — |
| LMArena Document | 1435 | — |

## Multilingual

- MiniMax-M3: 53.2 (#70)
- Qwen3.6 Plus: 53.5 (#66)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1420 | 1424 |
| LMArena Chinese | 1465 | 1478 |
| LMArena French | 1445 | 1454 |
| LMArena German | 1424 | 1451 |
| LMArena Japanese | 1381 | 1389 |
| LMArena Korean | 1372 | 1381 |
| LMArena Russian | 1430 | 1434 |
| LMArena Spanish | 1431 | 1432 |

## Instruction Following

- MiniMax-M3: 75.7 (#56)
- Qwen3.6 Plus: 75.2 (#70)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1433 | 1425 |

## Long Context

- MiniMax-M3: 44.2 (#68)
- Qwen3.6 Plus: 45.1 (#48)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1445 | 1440 |
| CL-bench | — | 20.3% |

## Writing & Preference

- MiniMax-M3: 62.3 (#79)
- Qwen3.6 Plus: 62.4 (#78)

| Benchmark | MiniMax-M3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1433 | 1437 |
| LMArena Creative Writing | 1405 | 1405 |
| LMArena Multi-Turn | 1441 | 1438 |
| EQ-Bench 4 | 1150 | — |

## FAQ

### Is MiniMax-M3 better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 43.5 on the Noometry Index. MiniMax-M3 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-M3 or Qwen3.6 Plus?

MiniMax-M3 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-M3 or Qwen3.6 Plus better for coding?

They score almost the same on coding (41.5 vs 40.6); test both on your own repository before choosing.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do MiniMax-M3 and Qwen3.6 Plus share?

30 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen3.6 Plus has 37.