Model comparison
Qwen3.5-Flash vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 4.0× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Qwen3.5-Flash scores higher in 0 categories and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 50.5 to 37.4.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 18.2% for Qwen3.5-Flash and 34.4% for Qwen3.7 Plus.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
Side by side
| Qwen3.5-Flash | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 42.5 | 45.3 |
| Released | 2026-02-23 | 2026-06-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $0.40 |
| Output $ / M tokens | $0.40 | $1.60 |
| Results tracked | 32 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
Qwen3.5-Flash: 34.2 (#242), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1412 | 1473 |
| FrontierCode | — | 10.2% |
| LMArena WebDev | 1244 | — |
| SciCode | — | 45.5% |
| ALE-Bench | 221.8 | — |
Agentic & Tool Use Not comparable
Qwen3.5-Flash: —, Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
| Vending-Bench 2 | 462.69 | — |
Reasoning Qwen3.7 Plus leads
Qwen3.5-Flash: 33.7 (#72), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| Chess Puzzles | 21% | 24% |
| LMArena Hard Prompts | 1403 | 1460 |
| Mystery Game Puzzles | 20% | 17% |
| DTBench | 82.9% | 84% |
| LMCA | 29.1% | 37.6% |
| Epoch Capabilities Index | 143.98 | 147.37 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
Math Qwen3.7 Plus leads
Qwen3.5-Flash: 37.4 (#158), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 18.2% | 34.4% |
| OTIS Mock AIME 2024-2025 | 84.4% | 93.3% |
| LMArena Math | 1407 | 1466 |
| FrontierMath (Feb 2025 set) | 6.2% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.7 Plus leads
Qwen3.5-Flash: 43.2 (#93), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 82.3% | 87.9% |
| LMArena Expert | 1407 | 1467 |
| SimpleQA Verified | 20.3% | — |
| Vectara Hallucination Rate | 10.5% | — |
Multimodal Not comparable
Qwen3.5-Flash: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Qwen3.5-Flash: 50.5 (#121), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1385 | 1445 |
| LMArena Chinese | 1446 | 1510 |
| LMArena French | 1412 | 1473 |
| LMArena German | 1390 | 1471 |
| LMArena Japanese | 1368 | 1413 |
| LMArena Korean | 1344 | 1415 |
| LMArena Russian | 1379 | 1457 |
| LMArena Spanish | 1400 | 1457 |
Instruction Following Qwen3.7 Plus leads
Qwen3.5-Flash: 72.6 (#139), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1374 | 1440 |
Long Context Qwen3.7 Plus leads
Qwen3.5-Flash: 42.4 (#124), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1392 | 1455 |
Writing & Preference Qwen3.7 Plus leads
Qwen3.5-Flash: 57.9 (#122), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Qwen3.5-Flash | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1397 | 1455 |
| LMArena Creative Writing | 1343 | 1439 |
| LMArena Multi-Turn | 1393 | 1460 |
Frequently asked questions
Is Qwen3.5-Flash better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 4.0× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5-Flash or Qwen3.7 Plus?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Qwen3.5-Flash or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 34.2 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 Plus share?
25 benchmarks have published results for both models. Qwen3.5-Flash has 32 scored results on Noometry and Qwen3.7 Plus has 32.