Model comparison
Qwen3.5 35B-A3B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 5.5× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Qwen3.5 35B-A3B scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 49.2 to 24.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 70% for Qwen3.5 35B-A3B and 95.6% for Qwen3.7 Max.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 262K.
- Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.5 35B-A3B | Qwen3.7 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 51.5 |
| Released | 2026-02-01 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.25 | $2.50 |
| Output $ / M tokens | $2 | $7.50 |
| Results tracked | 28 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Qwen3.5 35B-A3B: 33.8 (#251), Qwen3.7 Max: 50.4 (#45)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1254 | 1515 |
| SciCode | 29.3% | 48.8% |
| LMArena Coding | 1410 | 1498 |
| SWE-bench Verified | — | 77.3% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Not comparable
Qwen3.5 35B-A3B: —, Qwen3.7 Max: 22.1 (#135)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Qwen3.5 35B-A3B: 24.6 (#161), Qwen3.7 Max: 49.2 (#38)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| CritPt | 0.6% | 13.4% |
| Chess Puzzles | 10% | 19% |
| LMArena Hard Prompts | 1400 | 1483 |
| DTBench | 80% | 92.3% |
| LMCA | 29.5% | 44% |
| Epoch Capabilities Index | 142.52 | 153.68 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
Math Qwen3.7 Max leads
Qwen3.5 35B-A3B: 39.9 (#97), Qwen3.7 Max: 62.4 (#32)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 70% | 95.6% |
| LMArena Math | 1404 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| MathArena Final-Answer Competitions | 56% | — |
| ProofBench | — | 26% |
Knowledge Qwen3.7 Max leads
Qwen3.5 35B-A3B: 47.8 (#79), Qwen3.7 Max: 61.6 (#28)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 83.5% | 90.9% |
| LMArena Expert | 1408 | 1488 |
| SimpleQA Verified | — | 55.8% |
| Vectara Hallucination Rate | 10.5% | — |
Multilingual Qwen3.7 Max leads
Qwen3.5 35B-A3B: 50.0 (#127), Qwen3.7 Max: 56.9 (#15)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1378 | 1474 |
| LMArena Chinese | 1457 | 1530 |
| LMArena Russian | 1376 | 1484 |
| LMArena French | 1412 | — |
| LMArena German | 1367 | — |
| LMArena Japanese | 1325 | — |
| LMArena Korean | 1356 | — |
| LMArena Spanish | 1392 | — |
Instruction Following Qwen3.7 Max leads
Qwen3.5 35B-A3B: 72.8 (#128), Qwen3.7 Max: 76.7 (#38)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1379 | 1460 |
Long Context Qwen3.7 Max leads
Qwen3.5 35B-A3B: 42.4 (#127), Qwen3.7 Max: 45.4 (#40)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1389 | 1482 |
Writing & Preference Qwen3.7 Max leads
Qwen3.5 35B-A3B: 57.9 (#124), Qwen3.7 Max: 65.0 (#54)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1395 | 1476 |
| LMArena Creative Writing | 1346 | 1449 |
| LMArena Multi-Turn | 1390 | 1481 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Qwen3.5 35B-A3B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 5.5× 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 35B-A3B or Qwen3.7 Max?
Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Qwen3.5 35B-A3B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 262K.
How many benchmarks do Qwen3.5 35B-A3B and Qwen3.7 Max share?
21 benchmarks have published results for both models. Qwen3.5 35B-A3B has 28 scored results on Noometry and Qwen3.7 Max has 33.