# Qwen3.5-9B vs Qwen3 8B

> Qwen3.5-9B and Qwen3 8B score almost the same on the Noometry Index (33.8 vs 33.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/qwen3-5-9b-vs-qwen3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Qwen3.5-9B scores higher in 3 categories and Qwen3 8B in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3 8B leads 30.2 to 14.5.
- The biggest single-benchmark swing is GPQA Diamond: 79% for Qwen3.5-9B and 56.8% for Qwen3 8B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.18 / $0.70 for Qwen3 8B.
- Qwen3.5-9B accepts more context: 262K tokens versus 131K.

## Snapshot

| | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 33.8 | 33.7 |
| Rank | 236 | 238 |
| Context | 262K | 131K |
| Input $/M | $0.10 | $0.18 |
| Output $/M | $0.15 | $0.70 |
| Weights | Open | Open |

## Coding

- Qwen3.5-9B: 35.9 (#217)
- Qwen3 8B: 34.0 (#248)

| Benchmark | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| SciCode | 27.5% | 22.6% |

## Agentic & Tool Use

- Qwen3.5-9B: 14.5 (#151)
- Qwen3 8B: 30.2 (#78)

| Benchmark | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| Terminal-Bench | 9.2% | — |
| Berkeley Function Calling Leaderboard | — | 42.6% |

## Reasoning

- Qwen3.5-9B: 23.1 (#182)
- Qwen3 8B: 16.6 (#303)

| Benchmark | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| CritPt | 0.3% | 0% |
| Chess Puzzles | 12% | 5% |
| DTBench | 71.2% | 59.7% |
| LMCA | 24.5% | 8.8% |
| Epoch Capabilities Index | 139.46 | 136.17 |

## Math

- Qwen3.5-9B: 34.8 (#192)
- Qwen3 8B: 34.9 (#191)

| Benchmark | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 61.7% | 56.1% |
| MathArena Final-Answer Competitions | 48.5% | — |

## Knowledge

- Qwen3.5-9B: 46.0 (#84)
- Qwen3 8B: 36.1 (#173)

| Benchmark | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 79% | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |

## Long Context

- Qwen3.5-9B: —
- Qwen3 8B: 37.9 (#210)

| Benchmark | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |

## FAQ

### Is Qwen3.5-9B better than Qwen3 8B?

Qwen3.5-9B and Qwen3 8B score almost the same on the Noometry Index (33.8 vs 33.7), so choose on price, context window or the category you care about most.

### Which is cheaper, Qwen3.5-9B or Qwen3 8B?

Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.

### Is Qwen3.5-9B or Qwen3 8B better for coding?

Qwen3.5-9B scores higher on coding benchmarks: 35.9 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5-9B does, with 262K tokens against 131K.

### How many benchmarks do Qwen3.5-9B and Qwen3 8B share?

8 benchmarks have published results for both models. Qwen3.5-9B has 10 scored results on Noometry and Qwen3 8B has 11.