Model comparison
QwQ-32B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 39.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 17 benchmarks with published results for both. QwQ-32B scores higher in 2 categories and Step 3.5 Flash in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 50.6.
Side by side
| QwQ-32B | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 39.8 | 42.3 |
| Released | 2024-11-28 | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 36 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
QwQ-32B: 35.4 (#226), Step 3.5 Flash: 42.4 (#105)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1333 | 1436 |
| Aider Polyglot | 20.9% | — |
| BigCodeBench Instruct | 44.6% | — |
| LiveBench Coding | 72.2% | — |
| BigCodeBench Complete | 54.4% | — |
Reasoning QwQ-32B leads
QwQ-32B: 23.7 (#174), Step 3.5 Flash: 22.2 (#202)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1325 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| Chess Puzzles | 5% | — |
| LiveBench Reasoning | 83.5% | — |
| LiveBench Data Analysis | 65% | — |
| Epoch Capabilities Index | 137.6 | — |
| ForecastBench | 58.3 | — |
| LiveBench | 72% | — |
Math Step 3.5 Flash leads
QwQ-32B: 38.0 (#143), Step 3.5 Flash: 42.6 (#84)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1359 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 59.2% | — |
| LiveBench Math | 77.8% | — |
Knowledge Step 3.5 Flash leads
QwQ-32B: 37.2 (#158), Step 3.5 Flash: 39.6 (#132)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1324 | 1421 |
| GPQA Diamond | 65.3% | — |
| Confabulations | 15.6% | — |
Multilingual Step 3.5 Flash leads
QwQ-32B: 44.8 (#176), Step 3.5 Flash: 50.5 (#119)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1305 | 1385 |
| LMArena Chinese | 1378 | 1447 |
| LMArena French | 1336 | 1421 |
| LMArena German | 1313 | 1405 |
| LMArena Japanese | 1262 | 1354 |
| LMArena Korean | 1279 | 1352 |
| LMArena Russian | 1297 | 1385 |
| LMArena Spanish | 1354 | 1419 |
Instruction Following Too close to call
QwQ-32B: 72.6 (#137), Step 3.5 Flash: 73.1 (#124)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1297 | 1385 |
| LiveBench Instruction Following | 81.8% | — |
Long Context QwQ-32B leads
QwQ-32B: 49.0 (#11), Step 3.5 Flash: 42.8 (#117)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1308 | 1402 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Step 3.5 Flash leads
QwQ-32B: 50.6 (#180), Step 3.5 Flash: 58.8 (#113)
| Benchmark | QwQ-32B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1329 | 1403 |
| LMArena Creative Writing | 1288 | 1357 |
| LMArena Multi-Turn | 1314 | 1405 |
| Short-Story Creative Writing | 80.2% | — |
| EQ-Bench Creative Writing | 1257 | — |
| LiveBench Language | 51.4% | — |
Frequently asked questions
Is QwQ-32B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 39.8 on the Noometry Index.
Is QwQ-32B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 35.4 in the Noometry coding category.
How many benchmarks do QwQ-32B and Step 3.5 Flash share?
17 benchmarks have published results for both models. QwQ-32B has 36 scored results on Noometry and Step 3.5 Flash has 19.