Model comparison
Qwen3.5 397B-A17B vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 2.2× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Qwen3.5 397B-A17B scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 46.1.
- The biggest single-benchmark swing is NYT Connections (extended): 58.9% for Qwen3.5 397B-A17B and 74.1% for Qwen3.6 Max Preview.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.5 397B-A17B | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 46.0 | 51.5 |
| Released | 2026-02-01 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.60 | $1.30 |
| Output $ / M tokens | $3.60 | $7.80 |
| Results tracked | 36 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Qwen3.5 397B-A17B: 42.0 (#114), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1400 | 1482 |
| LMArena Coding | 1465 | 1471 |
| SWE-bench Verified | — | 76.7% |
Agentic & Tool Use Not comparable
Qwen3.5 397B-A17B: 33.3 (#53), Qwen3.6 Max Preview: —
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| APEX-Agents | 24.9% | — |
| τ²-bench Airline | 81.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 84.4% | — |
| τ²-bench Telecom | 97.8% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Qwen3.5 397B-A17B: 34.5 (#70), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| NYT Connections (extended) | 58.9% | 74.1% |
| Chess Puzzles | 13% | 20% |
| LMArena Hard Prompts | 1448 | 1457 |
| Mystery Game Puzzles | 18% | 19% |
| DTBench | 87.5% | 87.2% |
| LMCA | 37.9% | 42.5% |
| Epoch Capabilities Index | 146.65 | 149.24 |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 73.7% | — |
| Thematic Generalization | 65.1% | — |
Math Qwen3.6 Max Preview leads
Qwen3.5 397B-A17B: 46.1 (#73), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 91.1% |
| LMArena Math | 1454 | 1465 |
| FrontierMath (Tiers 1-3) | 31.2% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Qwen3.5 397B-A17B: 53.3 (#58), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 86.4% | 87.4% |
| LMArena Expert | 1462 | 1478 |
| SimpleQA Verified | — | 52% |
Multimodal Not comparable
Qwen3.5 397B-A17B: 40.7 (#44), Qwen3.6 Max Preview: —
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1263 | — |
Multilingual Too close to call
Qwen3.5 397B-A17B: 53.7 (#59), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1430 | 1437 |
| LMArena Chinese | 1500 | 1487 |
| LMArena French | 1461 | 1449 |
| LMArena Russian | 1429 | 1445 |
| LMArena Spanish | 1441 | 1454 |
| LMArena German | 1447 | — |
| LMArena Japanese | 1426 | — |
| LMArena Korean | 1384 | — |
Instruction Following Too close to call
Qwen3.5 397B-A17B: 75.0 (#77), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1424 | 1438 |
Long Context Too close to call
Qwen3.5 397B-A17B: 44.1 (#74), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1442 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Qwen3.5 397B-A17B: 62.3 (#79), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1438 | 1447 |
| LMArena Creative Writing | 1401 | 1435 |
| LMArena Multi-Turn | 1446 | 1456 |
| EQ-Bench Creative Writing | 1478 | — |
Frequently asked questions
Is Qwen3.5 397B-A17B better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 46.0 on the Noometry Index. Qwen3.5 397B-A17B costs 2.2× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5 397B-A17B or Qwen3.6 Max Preview?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Qwen3.5 397B-A17B or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Qwen3.5 397B-A17B and Qwen3.6 Max Preview share?
23 benchmarks have published results for both models. Qwen3.5 397B-A17B has 36 scored results on Noometry and Qwen3.6 Max Preview has 29.