# MiniMax-M2.7 vs Qwen3.5-9B

> MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.8 on the Noometry Index. Qwen3.5-9B costs 4.7× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-qwen3-5-9b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. MiniMax-M2.7 scores higher in 2 categories and Qwen3.5-9B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where MiniMax-M2.7 leads 25.1 to 14.5.
- The biggest single-benchmark swing is Terminal-Bench: 45.1% for MiniMax-M2.7 and 9.2% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- Qwen3.5-9B accepts more context: 262K tokens versus 205K.

## Snapshot

| | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 33.8 |
| Rank | 196 | 236 |
| Context | 205K | 262K |
| Input $/M | $0.30 | $0.10 |
| Output $/M | $1.20 | $0.15 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.8 (#120)
- Qwen3.5-9B: 35.9 (#217)

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| SciCode | 47% | 27.5% |
| LMArena WebDev | 1398 | — |
| WeirdML | 37% | — |
| LMArena Coding | 1454 | — |
| ALE-Bench | 599.25 | — |

## Agentic & Tool Use

- MiniMax-M2.7: 25.1 (#111)
- Qwen3.5-9B: 14.5 (#151)

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | 45.1% | 9.2% |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.7 (#253)
- Qwen3.5-9B: 23.1 (#182)

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| CritPt | 0.6% | 0.3% |
| Epoch Capabilities Index | 145.85 | 139.46 |
| NYT Connections (extended) | 24.7% | — |
| Chess Puzzles | — | 12% |
| Thematic Generalization | 39.3% | — |
| LMArena Hard Prompts | 1422 | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |

## Math

- MiniMax-M2.7: 25.9 (#263)
- Qwen3.5-9B: 34.8 (#192)

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 48.5% |
| OTIS Mock AIME 2024-2025 | — | 61.7% |
| ProofBench | 3% | — |
| LMArena Math | 1420 | — |

## Knowledge

- MiniMax-M2.7: 37.7 (#152)
- Qwen3.5-9B: 46.0 (#84)

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | — | 79% |
| Vectara Hallucination Rate | 12.9% | — |
| LMArena Expert | 1444 | — |

## Multilingual

- MiniMax-M2.7: 50.3 (#123)
- Qwen3.5-9B: —

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1382 | — |
| LMArena Chinese | 1441 | — |
| LMArena French | 1421 | — |
| LMArena German | 1398 | — |
| LMArena Japanese | 1262 | — |
| LMArena Korean | 1313 | — |
| LMArena Russian | 1383 | — |
| LMArena Spanish | 1403 | — |

## Instruction Following

- MiniMax-M2.7: 74.1 (#103)
- Qwen3.5-9B: —

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1405 | — |

## Long Context

- MiniMax-M2.7: 43.3 (#99)
- Qwen3.5-9B: —

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1419 | — |

## Writing & Preference

- MiniMax-M2.7: 58.9 (#112)
- Qwen3.5-9B: —

| Benchmark | MiniMax-M2.7 | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1405 | — |
| LMArena Creative Writing | 1354 | — |
| LMArena Multi-Turn | 1412 | — |

## FAQ

### Is MiniMax-M2.7 better than Qwen3.5-9B?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.8 on the Noometry Index. Qwen3.5-9B costs 4.7× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.

### Which is cheaper, MiniMax-M2.7 or Qwen3.5-9B?

Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

### Is MiniMax-M2.7 or Qwen3.5-9B better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5-9B does, with 262K tokens against 205K.

### How many benchmarks do MiniMax-M2.7 and Qwen3.5-9B share?

4 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3.5-9B has 10.