# MiniMax-M2.5 vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 38.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-5-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. MiniMax-M2.5 scores higher in 2 categories and Qwen3.7 Plus in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 49.3 to 25.8.
- The biggest single-benchmark swing is NYT Connections (extended): 16.8% for MiniMax-M2.5 and 74.8% for Qwen3.7 Plus.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.1 | 45.0 |
| Rank | 181 | 66 |
| Context | 205K | 1M |
| Input $/M | $0.30 | $0.40 |
| Output $/M | $1.20 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2.5: 47.9 (#53)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1380 | 1473 |
| FrontierCode | — | 10.2% |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1386 | — |
| SWE-bench Multilingual | 68.3% | — |
| SciCode | — | 45.5% |
| ALE-Bench | 618.17 | — |

## Agentic & Tool Use

- MiniMax-M2.5: 30.2 (#70)
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| OSWorld 2.0 | — | 2.8% |
| Vending-Bench 2 | -23.16 | — |

## Reasoning

- MiniMax-M2.5: 17.6 (#281)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 16.8% | 74.8% |
| LMArena Hard Prompts | 1372 | 1460 |
| Epoch Capabilities Index | 146.68 | 147.39 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |

## Math

- MiniMax-M2.5: 25.8 (#242)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1378 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | 4% | — |

## Knowledge

- MiniMax-M2.5: 38.6 (#132)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1378 | 1467 |
| GPQA Diamond | — | 87.9% |
| Vectara Hallucination Rate | 9.1% | — |

## Multimodal

- MiniMax-M2.5: —
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |

## Multilingual

- MiniMax-M2.5: 47.3 (#147)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1338 | 1445 |
| LMArena Chinese | 1392 | 1510 |
| LMArena French | 1363 | 1471 |
| LMArena German | 1361 | 1471 |
| LMArena Japanese | 1169 | 1411 |
| LMArena Korean | 1232 | 1416 |
| LMArena Russian | 1359 | 1457 |
| LMArena Spanish | 1354 | 1453 |

## Instruction Following

- MiniMax-M2.5: 71.7 (#143)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1353 | 1439 |

## Long Context

- MiniMax-M2.5: 37.4 (#211)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1367 | 1454 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |

## Writing & Preference

- MiniMax-M2.5: 54.1 (#149)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | MiniMax-M2.5 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1359 | 1454 |
| LMArena Creative Writing | 1331 | 1439 |
| LMArena Multi-Turn | 1364 | 1459 |
| EQ-Bench Creative Writing | 1361 | — |

## FAQ

### Is MiniMax-M2.5 better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 38.1 on the Noometry Index.

### Which is cheaper, MiniMax-M2.5 or Qwen3.7 Plus?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.

### Is MiniMax-M2.5 or Qwen3.7 Plus better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 36.1 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 205K.

### How many benchmarks do MiniMax-M2.5 and Qwen3.7 Plus share?

19 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3.7 Plus has 32.