Model comparison
Qwen Max vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 34.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Qwen Max scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 397B-A17B leads 44.9 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.1% for Qwen Max and 88.9% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 33K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Qwen Max | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.4 | 45.7 |
| Released | 2024-04-03 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 33K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $1.60 | $0.60 |
| Output $ / M tokens | $6.40 | $3.60 |
| Results tracked | 23 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Qwen Max: 30.3 (#288), Qwen3.5 397B-A17B: 41.7 (#108)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1288 | 1464 |
| Aider Polyglot | 21.8% | — |
| LMArena WebDev | — | 1400 |
Agentic & Tool Use Not comparable
Qwen Max: —, Qwen3.5 397B-A17B: 33.2 (#51)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| 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
Qwen Max: 24.1 (#154), Qwen3.5 397B-A17B: 33.6 (#62)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1270 | 1448 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.64 |
Math Qwen3.5 397B-A17B leads
Qwen Max: 21.0 (#272), Qwen3.5 397B-A17B: 44.9 (#64)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.1% | 88.9% |
| LMArena Math | 1275 | 1455 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Qwen3.5 397B-A17B leads
Qwen Max: 30.3 (#222), Qwen3.5 397B-A17B: 53.3 (#53)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 56.1% | 86.4% |
| LMArena Expert | 1248 | 1461 |
Multimodal Not comparable
Qwen Max: —, Qwen3.5 397B-A17B: 40.0 (#42)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1262 |
Multilingual Qwen3.5 397B-A17B leads
Qwen Max: 42.0 (#197), Qwen3.5 397B-A17B: 54.0 (#56)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1263 | 1431 |
| LMArena Chinese | 1254 | 1501 |
| LMArena French | 1329 | 1461 |
| LMArena German | 1254 | 1447 |
| LMArena Japanese | 1205 | 1427 |
| LMArena Korean | 1141 | 1382 |
| LMArena Russian | 1274 | 1429 |
| LMArena Spanish | 1290 | 1443 |
Instruction Following Qwen3.5 397B-A17B leads
Qwen Max: 66.7 (#203), Qwen3.5 397B-A17B: 75.2 (#73)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1262 | 1424 |
Long Context Qwen3.5 397B-A17B leads
Qwen Max: 39.4 (#175), Qwen3.5 397B-A17B: 44.1 (#71)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1289 | 1442 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Qwen3.5 397B-A17B leads
Qwen Max: 48.0 (#200), Qwen3.5 397B-A17B: 62.5 (#74)
| Benchmark | Qwen Max | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1282 | 1438 |
| LMArena Creative Writing | 1248 | 1401 |
| LMArena Multi-Turn | 1277 | 1447 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is Qwen Max better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 34.4 on the Noometry Index.
Which is cheaper, Qwen Max or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Qwen Max or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 41.7 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 33K.
How many benchmarks do Qwen Max and Qwen3.5 397B-A17B share?
19 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen3.5 397B-A17B has 36.