Model comparison
Qwen3.5 35B-A3B vs QwQ-32B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 39.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Qwen3.5 35B-A3B scores higher in 6 categories and QwQ-32B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.8 to 37.2.
- The biggest single-benchmark swing is GPQA Diamond: 83.5% for Qwen3.5 35B-A3B and 65.3% for QwQ-32B.
Side by side
| Qwen3.5 35B-A3B | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 39.8 |
| Released | 2026-02-01 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 28 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Qwen3.5 35B-A3B: 33.8 (#251), QwQ-32B: 35.4 (#226)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| LMArena Coding | 1410 | 1333 |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1254 | — |
| SciCode | 29.3% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
Reasoning Too close to call
Qwen3.5 35B-A3B: 24.6 (#161), QwQ-32B: 23.7 (#174)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| Chess Puzzles | 10% | 5% |
| LMArena Hard Prompts | 1400 | 1325 |
| Epoch Capabilities Index | 142.52 | 137.6 |
| CritPt | 0.6% | — |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 80% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 29.5% | — |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math Qwen3.5 35B-A3B leads
Qwen3.5 35B-A3B: 39.9 (#97), QwQ-32B: 38.0 (#143)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 70% | 59.2% |
| LMArena Math | 1404 | 1359 |
| MathArena Final-Answer Competitions | 56% | — |
| LiveBench Math | — | 77.8% |
Knowledge Qwen3.5 35B-A3B leads
Qwen3.5 35B-A3B: 47.8 (#79), QwQ-32B: 37.2 (#158)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 83.5% | 65.3% |
| LMArena Expert | 1408 | 1324 |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 10.5% | — |
Multilingual Qwen3.5 35B-A3B leads
Qwen3.5 35B-A3B: 50.0 (#127), QwQ-32B: 44.8 (#176)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1378 | 1305 |
| LMArena Chinese | 1457 | 1378 |
| LMArena French | 1412 | 1336 |
| LMArena German | 1367 | 1313 |
| LMArena Japanese | 1325 | 1262 |
| LMArena Korean | 1356 | 1279 |
| LMArena Russian | 1376 | 1297 |
| LMArena Spanish | 1392 | 1354 |
Instruction Following Too close to call
Qwen3.5 35B-A3B: 72.8 (#128), QwQ-32B: 72.6 (#137)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1379 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Qwen3.5 35B-A3B: 42.4 (#127), QwQ-32B: 49.0 (#11)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1389 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Qwen3.5 35B-A3B leads
Qwen3.5 35B-A3B: 57.9 (#124), QwQ-32B: 50.6 (#180)
| Benchmark | Qwen3.5 35B-A3B | QwQ-32B |
|---|---|---|
| LMArena Text | 1395 | 1329 |
| LMArena Creative Writing | 1346 | 1288 |
| LMArena Multi-Turn | 1390 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Qwen3.5 35B-A3B better than QwQ-32B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 39.8 on the Noometry Index.
Is Qwen3.5 35B-A3B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 33.8 in the Noometry coding category.
How many benchmarks do Qwen3.5 35B-A3B and QwQ-32B share?
21 benchmarks have published results for both models. Qwen3.5 35B-A3B has 28 scored results on Noometry and QwQ-32B has 36.