# MiniMax-M2.7 vs Qwen3 Max

> Qwen3 Max is the stronger model overall, scoring 43.5 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 4.6× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-qwen3-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. MiniMax-M2.7 scores higher in 1 category and Qwen3 Max in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 Max leads 37.6 to 24.9.
- The biggest single-benchmark swing is NYT Connections (extended): 24.7% for MiniMax-M2.7 and 30.1% for Qwen3 Max.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 43.5 |
| Rank | 188 | 82 |
| Context | 205K | 262K |
| Input $/M | $0.30 | $1.20 |
| Output $/M | $1.20 | $6 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2.7: 41.4 (#115)
- Qwen3 Max: 42.4 (#93)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1454 | 1456 |
| ALE-Bench | 599.25 | 370.45 |
| LMArena WebDev | 1397 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |

## Agentic & Tool Use

- MiniMax-M2.7: 24.9 (#103)
- Qwen3 Max: —

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | — | 71.56 |

## Reasoning

- MiniMax-M2.7: 19.0 (#248)
- Qwen3 Max: 22.0 (#186)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 24.7% | 30.1% |
| LMArena Hard Prompts | 1422 | 1448 |
| Epoch Capabilities Index | 145.84 | 142.41 |
| Kagi LLM Benchmark | — | 72.5% |
| CritPt | 0.6% | — |
| Chess Puzzles | — | 4% |
| Thematic Generalization | 39.3% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |

## Math

- MiniMax-M2.7: 24.9 (#254)
- Qwen3 Max: 37.6 (#94)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| LMArena Math | 1420 | 1447 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| ProofBench | 3% | — |
| MATH Level 5 | — | 97.1% |

## Knowledge

- MiniMax-M2.7: 37.1 (#151)
- Qwen3 Max: 48.1 (#72)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1443 | 1457 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
| Vectara Hallucination Rate | 12.9% | — |

## Multilingual

- MiniMax-M2.7: 50.5 (#120)
- Qwen3 Max: 53.9 (#58)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1382 | 1429 |
| LMArena Chinese | 1439 | 1479 |
| LMArena French | 1422 | 1450 |
| LMArena German | 1398 | 1463 |
| LMArena Japanese | 1261 | 1399 |
| LMArena Korean | 1313 | 1397 |
| LMArena Russian | 1383 | 1428 |
| LMArena Spanish | 1403 | 1463 |

## Instruction Following

- MiniMax-M2.7: 74.2 (#101)
- Qwen3 Max: 75.0 (#81)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1404 | 1420 |

## Long Context

- MiniMax-M2.7: 43.3 (#94)
- Qwen3 Max: 41.6 (#129)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1419 | 1439 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |

## Writing & Preference

- MiniMax-M2.7: 59.1 (#107)
- Qwen3 Max: 62.6 (#72)

| Benchmark | MiniMax-M2.7 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1404 | 1439 |
| LMArena Creative Writing | 1354 | 1401 |
| LMArena Multi-Turn | 1413 | 1446 |

## FAQ

### Is MiniMax-M2.7 better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.5 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 4.6× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.

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

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

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

They score almost the same on coding (41.4 vs 42.4); test both on your own repository before choosing.

### Which has the bigger context window?

Qwen3 Max does, with 262K tokens against 205K.

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

20 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3 Max has 33.