# MiniMax-M2.5 vs Qwen Max

> MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 34.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-5-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiniMax-M2.5 scores higher in 6 categories and Qwen Max in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 47.9 to 30.3.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- MiniMax-M2.5 accepts more context: 205K tokens versus 33K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.1 | 34.4 |
| Rank | 181 | 226 |
| Context | 205K | 33K |
| Input $/M | $0.30 | $1.60 |
| Output $/M | $1.20 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2.5: 47.9 (#53)
- Qwen Max: 30.3 (#288)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Coding | 1380 | 1288 |
| SWE-bench Verified (bash only) | 75.8% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1386 | — |
| SWE-bench Multilingual | 68.3% | — |
| ALE-Bench | 618.17 | — |

## Agentic & Tool Use

- MiniMax-M2.5: 30.2 (#70)
- Qwen Max: —

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |

## Reasoning

- MiniMax-M2.5: 17.6 (#281)
- Qwen Max: 24.1 (#154)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1270 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Epoch Capabilities Index | 146.68 | — |

## Math

- MiniMax-M2.5: 25.8 (#242)
- Qwen Max: 21.0 (#272)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Math | 1378 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| ProofBench | 4% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- MiniMax-M2.5: 38.6 (#132)
- Qwen Max: 30.3 (#222)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Expert | 1378 | 1248 |
| GPQA Diamond | — | 56.1% |
| Vectara Hallucination Rate | 9.1% | — |

## Multilingual

- MiniMax-M2.5: 47.3 (#147)
- Qwen Max: 42.0 (#197)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1338 | 1263 |
| LMArena Chinese | 1392 | 1254 |
| LMArena French | 1363 | 1329 |
| LMArena German | 1361 | 1254 |
| LMArena Japanese | 1169 | 1205 |
| LMArena Korean | 1232 | 1141 |
| LMArena Russian | 1359 | 1274 |
| LMArena Spanish | 1354 | 1290 |

## Instruction Following

- MiniMax-M2.5: 71.7 (#143)
- Qwen Max: 66.7 (#203)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1353 | 1262 |

## Long Context

- MiniMax-M2.5: 37.4 (#211)
- Qwen Max: 39.4 (#175)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1367 | 1289 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |

## Writing & Preference

- MiniMax-M2.5: 54.1 (#149)
- Qwen Max: 48.0 (#200)

| Benchmark | MiniMax-M2.5 | Qwen Max |
|---|---|---|
| LMArena Text | 1359 | 1282 |
| LMArena Creative Writing | 1331 | 1248 |
| LMArena Multi-Turn | 1364 | 1277 |
| EQ-Bench Creative Writing | 1361 | — |

## FAQ

### Is MiniMax-M2.5 better than Qwen Max?

MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 34.4 on the Noometry Index.

### Which is cheaper, MiniMax-M2.5 or Qwen Max?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is MiniMax-M2.5 or Qwen Max better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 33K.

### How many benchmarks do MiniMax-M2.5 and Qwen Max share?

17 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen Max has 23.