# MiniMax-M2.7 vs Qwen2.5-Coder-32B

> MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-qwen2-5-coder-32b
- Last updated: 2026-10-12
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. MiniMax-M2.7 scores higher in 6 categories and Qwen2.5-Coder-32B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.7 leads 41.8 to 22.6.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- MiniMax-M2.7 accepts more context: 205K tokens versus 33K.

## Snapshot

| | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 33.4 |
| Rank | 196 | 245 |
| Context | 205K | 33K |
| Input $/M | $0.30 | $0.66 |
| Output $/M | $1.20 | $1 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.8 (#120)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1454 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1398 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 599.25 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Agentic & Tool Use

- MiniMax-M2.7: 25.1 (#111)
- Qwen2.5-Coder-32B: —

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.7 (#253)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1251 |
| Epoch Capabilities Index | 145.85 | 119.49 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- MiniMax-M2.7: 25.9 (#263)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1420 | 1251 |
| ProofBench | 3% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- MiniMax-M2.7: 37.7 (#152)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1444 | 1221 |
| Vectara Hallucination Rate | 12.9% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- MiniMax-M2.7: 50.3 (#123)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1382 | 1205 |
| LMArena Chinese | 1441 | 1222 |
| LMArena Russian | 1383 | 1228 |
| LMArena French | 1421 | — |
| LMArena German | 1398 | — |
| LMArena Japanese | 1262 | — |
| LMArena Korean | 1313 | — |
| LMArena Spanish | 1403 | — |

## Instruction Following

- MiniMax-M2.7: 74.1 (#103)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- MiniMax-M2.7: 43.3 (#99)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1419 | 1251 |

## Writing & Preference

- MiniMax-M2.7: 58.9 (#112)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | MiniMax-M2.7 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1405 | 1230 |
| LMArena Creative Writing | 1354 | 1174 |
| LMArena Multi-Turn | 1412 | 1222 |
| LiveBench Language | — | 23.3% |

## FAQ

### Is MiniMax-M2.7 better than Qwen2.5-Coder-32B?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.4 on the Noometry Index.

### Which is cheaper, MiniMax-M2.7 or Qwen2.5-Coder-32B?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

### Is MiniMax-M2.7 or Qwen2.5-Coder-32B better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 22.6 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 33K.

### How many benchmarks do MiniMax-M2.7 and Qwen2.5-Coder-32B share?

13 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen2.5-Coder-32B has 31.