Model comparison
Qwen3.5 35B-A3B vs Qwen3.5-Flash
Qwen3.5 35B-A3B and Qwen3.5-Flash score almost the same on the Noometry Index (42.0 vs 42.5), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Qwen3.5 35B-A3B scores higher in 3 categories and Qwen3.5-Flash in 5 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5-Flash leads 33.7 to 24.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 70% for Qwen3.5 35B-A3B and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
- Qwen3.5-Flash 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 | Qwen3.5-Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 42.5 |
| Released | 2026-02-01 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.25 | $0.10 |
| Output $ / M tokens | $2 | $0.40 |
| Results tracked | 28 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen3.5 35B-A3B: 33.8 (#251), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1254 | 1244 |
| LMArena Coding | 1410 | 1412 |
| SciCode | 29.3% | — |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
Qwen3.5 35B-A3B: —, Qwen3.5-Flash: —
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Qwen3.5 35B-A3B: 24.6 (#161), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 10% | 21% |
| LMArena Hard Prompts | 1400 | 1403 |
| DTBench | 80% | 82.9% |
| LMCA | 29.5% | 29.1% |
| Epoch Capabilities Index | 142.52 | 143.98 |
| CritPt | 0.6% | — |
| Mystery Game Puzzles | — | 20% |
Math Qwen3.5 35B-A3B leads
Qwen3.5 35B-A3B: 39.9 (#97), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 70% | 84.4% |
| LMArena Math | 1404 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| MathArena Final-Answer Competitions | 56% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5 35B-A3B leads
Qwen3.5 35B-A3B: 47.8 (#79), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 83.5% | 82.3% |
| Vectara Hallucination Rate | 10.5% | 10.5% |
| LMArena Expert | 1408 | 1407 |
| SimpleQA Verified | — | 20.3% |
Multilingual Too close to call
Qwen3.5 35B-A3B: 50.0 (#127), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1378 | 1385 |
| LMArena Chinese | 1457 | 1446 |
| LMArena French | 1412 | 1412 |
| LMArena German | 1367 | 1390 |
| LMArena Japanese | 1325 | 1368 |
| LMArena Korean | 1356 | 1344 |
| LMArena Russian | 1376 | 1379 |
| LMArena Spanish | 1392 | 1400 |
Instruction Following Too close to call
Qwen3.5 35B-A3B: 72.8 (#128), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1379 | 1374 |
Long Context Too close to call
Qwen3.5 35B-A3B: 42.4 (#127), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1389 | 1392 |
Writing & Preference Too close to call
Qwen3.5 35B-A3B: 57.9 (#124), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Qwen3.5 35B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1395 | 1397 |
| LMArena Creative Writing | 1346 | 1343 |
| LMArena Multi-Turn | 1390 | 1393 |
Frequently asked questions
Is Qwen3.5 35B-A3B better than Qwen3.5-Flash?
Qwen3.5 35B-A3B and Qwen3.5-Flash score almost the same on the Noometry Index (42.0 vs 42.5), so choose on price, context window or the category you care about most.
Which is cheaper, Qwen3.5 35B-A3B or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.
Is Qwen3.5 35B-A3B or Qwen3.5-Flash better for coding?
They score almost the same on coding (33.8 vs 34.2); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 262K.
How many benchmarks do Qwen3.5 35B-A3B and Qwen3.5-Flash share?
25 benchmarks have published results for both models. Qwen3.5 35B-A3B has 28 scored results on Noometry and Qwen3.5-Flash has 32.