Model comparison
Qwen3.6 35B-A3B vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 37.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Qwen3.6 35B-A3B scores higher in 2 categories and Qwen3.7 Plus in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 50.5 to 38.9.
- The biggest single-benchmark swing is NYT Connections (extended): 41.6% for Qwen3.6 35B-A3B and 74.8% for Qwen3.7 Plus.
- Qwen3.6 35B-A3B is cheaper at $0.25 / $1.49 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 262K.
- Qwen3.6 35B-A3B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.6 35B-A3B | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 37.6 | 45.3 |
| Released | 2026-04-01 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.25 | $0.40 |
| Output $ / M tokens | $1.49 | $1.60 |
| Results tracked | 14 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen3.6 35B-A3B: 37.2 (#196), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| SciCode | 35.8% | 45.5% |
| FrontierCode | — | 10.2% |
| WeirdML | 34.5% | — |
| LMArena Coding | — | 1473 |
Agentic & Tool Use Too close to call
Qwen3.6 35B-A3B: 22.1 (#134), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 23% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Qwen3.6 35B-A3B: 28.0 (#109), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 41.6% | 74.8% |
| CritPt | 0.3% | 9.1% |
| Chess Puzzles | 26% | 24% |
| Mystery Game Puzzles | 22% | 17% |
| DTBench | 73.9% | 84% |
| LMCA | 29.7% | 37.6% |
| Epoch Capabilities Index | 143.93 | 147.37 |
| LMArena Hard Prompts | — | 1460 |
| Surface Evolver Bench | 44.4% | — |
Math Qwen3.7 Plus leads
Qwen3.6 35B-A3B: 38.9 (#121), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20.4% | 34.4% |
| OTIS Mock AIME 2024-2025 | 86.7% | 93.3% |
| LMArena Math | — | 1466 |
Knowledge Qwen3.7 Plus leads
Qwen3.6 35B-A3B: 51.3 (#68), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 84.8% | 87.9% |
| LMArena Expert | — | 1467 |
Multimodal Not comparable
Qwen3.6 35B-A3B: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Qwen3.6 35B-A3B: —, Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | — | 1445 |
| LMArena Chinese | — | 1510 |
| LMArena French | — | 1473 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Russian | — | 1457 |
| LMArena Spanish | — | 1457 |
Instruction Following Not comparable
Qwen3.6 35B-A3B: —, Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | — | 1440 |
Long Context Not comparable
Qwen3.6 35B-A3B: —, Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Qwen3.6 35B-A3B: —, Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Qwen3.6 35B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | — | 1455 |
| LMArena Creative Writing | — | 1439 |
| LMArena Multi-Turn | — | 1460 |
Frequently asked questions
Is Qwen3.6 35B-A3B better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 37.6 on the Noometry Index.
Which is cheaper, Qwen3.6 35B-A3B or Qwen3.7 Plus?
Qwen3.6 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $1.49 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Qwen3.6 35B-A3B or Qwen3.7 Plus better for coding?
They score almost the same on coding (37.2 vs 36.6); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 262K.
How many benchmarks do Qwen3.6 35B-A3B and Qwen3.7 Plus share?
11 benchmarks have published results for both models. Qwen3.6 35B-A3B has 14 scored results on Noometry and Qwen3.7 Plus has 32.