Model comparison
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.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)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.
Side by side
| Qwen3.5-9B | Qwen3 8B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 33.8 | 33.7 |
| Released | 2026-02-23 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.10 | $0.18 |
| Output $ / M tokens | $0.15 | $0.70 |
| Results tracked | 10 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5-9B leads
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 8B leads
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 leads
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 Too close to call
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 leads
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 Not comparable
Qwen3.5-9B: —, Qwen3 8B: 37.9 (#210)
| Benchmark | Qwen3.5-9B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Frequently asked questions
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.