Model comparison
Qwen3.5-9B vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.0 to 33.3 on the Noometry Index. Qwen3.5-9B costs 27× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Qwen3.5-9B scores higher in 0 categories and Qwen3.8 Max in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 33.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 61.7% for Qwen3.5-9B and 100% for Qwen3.8 Max.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 262K.
- Qwen3.5-9B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.5-9B | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 33.3 | 56.0 |
| Released | 2026-02-23 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.15 | $6 |
| Results tracked | 10 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen3.5-9B: 35.3 (#213), Qwen3.8 Max: 52.3 (#30)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| SciCode | 27.5% | 52.9% |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1671 |
| FrontierSWE | — | 15.8% |
| LMArena Coding | — | 1499 |
Agentic & Tool Use Qwen3.8 Max leads
Qwen3.5-9B: 14.4 (#143), Qwen3.8 Max: 42.6 (#17)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| Terminal-Bench | 9.2% | — |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Qwen3.5-9B: 22.5 (#178), Qwen3.8 Max: 53.4 (#26)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| CritPt | 0.3% | 20% |
| Chess Puzzles | 12% | 40% |
| DTBench | 71.2% | 92% |
| LMCA | 24.5% | 46.2% |
| Epoch Capabilities Index | 139.45 | 156.69 |
| NYT Connections (extended) | — | 88.3% |
| LMArena Hard Prompts | — | 1493 |
| Mystery Game Puzzles | — | 38% |
Math Qwen3.8 Max leads
Qwen3.5-9B: 33.5 (#174), Qwen3.8 Max: 73.1 (#15)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 61.7% | 100% |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| MathArena Final-Answer Competitions | 48.5% | — |
| ProofBench | — | 58% |
| LMArena Math | — | 1498 |
Knowledge Qwen3.8 Max leads
Qwen3.5-9B: 46.0 (#77), Qwen3.8 Max: 61.7 (#25)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 79% | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1504 |
Multimodal Not comparable
Qwen3.5-9B: —, Qwen3.8 Max: 36.9 (#70)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Qwen3.5-9B: —, Qwen3.8 Max: 56.6 (#18)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1468 |
| LMArena Chinese | — | 1537 |
| LMArena French | — | 1502 |
| LMArena German | — | 1489 |
| LMArena Japanese | — | 1466 |
| LMArena Korean | — | 1467 |
| LMArena Russian | — | 1478 |
| LMArena Spanish | — | 1495 |
Instruction Following Not comparable
Qwen3.5-9B: —, Qwen3.8 Max: 77.7 (#19)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1478 |
Long Context Not comparable
Qwen3.5-9B: —, Qwen3.8 Max: 45.5 (#30)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1486 |
Writing & Preference Not comparable
Qwen3.5-9B: —, Qwen3.8 Max: 67.0 (#31)
| Benchmark | Qwen3.5-9B | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1480 |
| LMArena Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1487 |
Frequently asked questions
Is Qwen3.5-9B better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.0 to 33.3 on the Noometry Index. Qwen3.5-9B costs 27× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5-9B or Qwen3.8 Max?
Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Qwen3.5-9B or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 35.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 262K.
How many benchmarks do Qwen3.5-9B and Qwen3.8 Max share?
8 benchmarks have published results for both models. Qwen3.5-9B has 10 scored results on Noometry and Qwen3.8 Max has 38.