# Qwen Max vs Qwen3.5-9B

> Qwen Max is the stronger model overall, scoring 34.4 to 33.3 on the Noometry Index. Qwen3.5-9B costs 25× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/qwen-max-vs-qwen3-5-9b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Qwen Max scores higher in 1 category and Qwen3.5-9B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-9B leads 46.0 to 30.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.1% for Qwen Max and 61.7% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Qwen3.5-9B accepts more context: 262K tokens versus 33K.
- Qwen3.5-9B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen Max | Qwen3.5-9B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.4 | 33.3 |
| Rank | 226 | 235 |
| Context | 33K | 262K |
| Input $/M | $1.60 | $0.10 |
| Output $/M | $6.40 | $0.15 |
| Weights | Proprietary | Open |

## Coding

- Qwen Max: 30.3 (#288)
- Qwen3.5-9B: 35.3 (#213)

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| Aider Polyglot | 21.8% | — |
| SciCode | — | 27.5% |
| LMArena Coding | 1288 | — |

## Agentic & Tool Use

- Qwen Max: —
- Qwen3.5-9B: 14.4 (#143)

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |

## Reasoning

- Qwen Max: 24.1 (#154)
- Qwen3.5-9B: 22.5 (#178)

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| CritPt | — | 0.3% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | 1270 | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |
| Epoch Capabilities Index | — | 139.45 |

## Math

- Qwen Max: 21.0 (#272)
- Qwen3.5-9B: 33.5 (#174)

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.1% | 61.7% |
| MathArena Final-Answer Competitions | — | 48.5% |
| LMArena Math | 1275 | — |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |

## Knowledge

- Qwen Max: 30.3 (#222)
- Qwen3.5-9B: 46.0 (#77)

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 56.1% | 79% |
| LMArena Expert | 1248 | — |

## Multilingual

- Qwen Max: 42.0 (#197)
- Qwen3.5-9B: —

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1263 | — |
| LMArena Chinese | 1254 | — |
| LMArena French | 1329 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1205 | — |
| LMArena Korean | 1141 | — |
| LMArena Russian | 1274 | — |
| LMArena Spanish | 1290 | — |

## Instruction Following

- Qwen Max: 66.7 (#203)
- Qwen3.5-9B: —

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1262 | — |

## Long Context

- Qwen Max: 39.4 (#175)
- Qwen3.5-9B: —

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| LMArena Longer Query | 1289 | — |

## Writing & Preference

- Qwen Max: 48.0 (#200)
- Qwen3.5-9B: —

| Benchmark | Qwen Max | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1282 | — |
| LMArena Creative Writing | 1248 | — |
| LMArena Multi-Turn | 1277 | — |

## FAQ

### Is Qwen Max better than Qwen3.5-9B?

Qwen Max is the stronger model overall, scoring 34.4 to 33.3 on the Noometry Index. Qwen3.5-9B costs 25× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.

### Which is cheaper, Qwen Max 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; Qwen Max lists at $1.60 and $6.40.

### Is Qwen Max or Qwen3.5-9B better for coding?

Qwen3.5-9B scores higher on coding benchmarks: 35.3 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5-9B does, with 262K tokens against 33K.

### How many benchmarks do Qwen Max and Qwen3.5-9B share?

2 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen3.5-9B has 10.