Model comparison
Qwen3.5 397B-A17B vs Qwen3.5-9B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.8 on the Noometry Index. Qwen3.5-9B costs 12× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Qwen3.5 397B-A17B scores higher in 5 categories and Qwen3.5-9B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3.5 397B-A17B leads 33.3 to 14.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Qwen3.5 397B-A17B and 61.7% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
Side by side
| Qwen3.5 397B-A17B | Qwen3.5-9B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 46.0 | 33.8 |
| Released | 2026-02-01 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.60 | $0.10 |
| Output $ / M tokens | $3.60 | $0.15 |
| Results tracked | 36 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 42.0 (#114), Qwen3.5-9B: 35.9 (#217)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| LMArena WebDev | 1400 | — |
| SciCode | — | 27.5% |
| LMArena Coding | 1465 | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 33.3 (#53), Qwen3.5-9B: 14.5 (#151)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| APEX-Agents | 24.9% | — |
| τ²-bench Airline | 81.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 84.4% | — |
| τ²-bench Telecom | 97.8% | — |
Reasoning Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 34.5 (#70), Qwen3.5-9B: 23.1 (#182)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| Chess Puzzles | 13% | 12% |
| DTBench | 87.5% | 71.2% |
| LMCA | 37.9% | 24.5% |
| Epoch Capabilities Index | 146.65 | 139.46 |
| Kagi LLM Benchmark | 73.7% | — |
| NYT Connections (extended) | 58.9% | — |
| CritPt | — | 0.3% |
| Thematic Generalization | 65.1% | — |
| LMArena Hard Prompts | 1448 | — |
| Mystery Game Puzzles | 18% | — |
Math Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 46.1 (#73), Qwen3.5-9B: 34.8 (#192)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 61.7% |
| FrontierMath (Tiers 1-3) | 31.2% | — |
| MathArena Final-Answer Competitions | — | 48.5% |
| LMArena Math | 1454 | — |
Knowledge Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 53.3 (#58), Qwen3.5-9B: 46.0 (#84)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 86.4% | 79% |
| LMArena Expert | 1462 | — |
Multimodal Not comparable
Qwen3.5 397B-A17B: 40.7 (#44), Qwen3.5-9B: —
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| LMArena Vision | 1263 | — |
Multilingual Not comparable
Qwen3.5 397B-A17B: 53.7 (#59), Qwen3.5-9B: —
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1430 | — |
| LMArena Chinese | 1500 | — |
| LMArena French | 1461 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1426 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1441 | — |
Instruction Following Not comparable
Qwen3.5 397B-A17B: 75.0 (#77), Qwen3.5-9B: —
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1424 | — |
Long Context Not comparable
Qwen3.5 397B-A17B: 44.1 (#74), Qwen3.5-9B: —
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1442 | — |
Writing & Preference Not comparable
Qwen3.5 397B-A17B: 62.3 (#79), Qwen3.5-9B: —
| Benchmark | Qwen3.5 397B-A17B | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1438 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1478 | — |
| LMArena Multi-Turn | 1446 | — |
Frequently asked questions
Is Qwen3.5 397B-A17B better than Qwen3.5-9B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.8 on the Noometry Index. Qwen3.5-9B costs 12× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5 397B-A17B 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; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is Qwen3.5 397B-A17B or Qwen3.5-9B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Qwen3.5 397B-A17B and Qwen3.5-9B share?
6 benchmarks have published results for both models. Qwen3.5 397B-A17B has 36 scored results on Noometry and Qwen3.5-9B has 10.