Model comparison
Qwen3.5-Flash vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 42.3 on the Noometry Index. Qwen3.5-Flash costs 21× less per token, which makes it the better buy when Qwen3.7 Max'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-Flash scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.3 to 36.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 18.2% for Qwen3.5-Flash and 64.6% for Qwen3.7 Max.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
Side by side
| Qwen3.5-Flash | Qwen3.7 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 42.3 | 51.4 |
| Released | 2026-02-23 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $2.50 |
| Output $ / M tokens | $0.40 | $7.50 |
| Results tracked | 32 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Qwen3.5-Flash: 33.9 (#234), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1243 | 1515 |
| LMArena Coding | 1412 | 1498 |
| ALE-Bench | 221.8 | 1,189 |
| SWE-bench Verified | — | 77.3% |
| SciCode | — | 48.8% |
Agentic & Tool Use Not comparable
Qwen3.5-Flash: —, Qwen3.7 Max: 21.8 (#129)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
| Vending-Bench 2 | 462.69 | — |
Reasoning Qwen3.7 Max leads
Qwen3.5-Flash: 32.9 (#63), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| Chess Puzzles | 21% | 19% |
| LMArena Hard Prompts | 1404 | 1483 |
| Mystery Game Puzzles | 20% | 32% |
| DTBench | 82.9% | 92.3% |
| LMCA | 29.1% | 44% |
| Epoch Capabilities Index | 143.98 | 153.74 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| EBR-Bench | — | 9.5% |
Math Qwen3.7 Max leads
Qwen3.5-Flash: 36.3 (#117), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 18.2% | 64.6% |
| OTIS Mock AIME 2024-2025 | 84.4% | 95.6% |
| LMArena Math | 1407 | 1488 |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| FrontierMath (Feb 2025 set) | 6.2% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.7 Max leads
Qwen3.5-Flash: 43.2 (#84), Qwen3.7 Max: 61.7 (#24)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 82.3% | 90.9% |
| SimpleQA Verified | 20.3% | 55.8% |
| LMArena Expert | 1408 | 1488 |
| Vectara Hallucination Rate | 10.5% | — |
Multilingual Qwen3.7 Max leads
Qwen3.5-Flash: 50.7 (#116), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1385 | 1475 |
| LMArena Chinese | 1446 | 1533 |
| LMArena Russian | 1379 | 1482 |
| LMArena French | 1412 | — |
| LMArena German | 1389 | — |
| LMArena Japanese | 1369 | — |
| LMArena Korean | 1344 | — |
| LMArena Spanish | 1399 | — |
Instruction Following Qwen3.7 Max leads
Qwen3.5-Flash: 72.8 (#133), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1374 | 1460 |
Long Context Qwen3.7 Max leads
Qwen3.5-Flash: 42.4 (#119), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1392 | 1484 |
Writing & Preference Qwen3.7 Max leads
Qwen3.5-Flash: 58.2 (#117), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1397 | 1476 |
| LMArena Creative Writing | 1343 | 1450 |
| LMArena Multi-Turn | 1393 | 1482 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Qwen3.5-Flash better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 42.3 on the Noometry Index. Qwen3.5-Flash costs 21× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5-Flash or Qwen3.7 Max?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Qwen3.5-Flash or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 33.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Qwen3.5-Flash and Qwen3.7 Max share?
23 benchmarks have published results for both models. Qwen3.5-Flash has 32 scored results on Noometry and Qwen3.7 Max has 33.