Model comparison
QwQ-32B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 13 benchmarks with published results for both. QwQ-32B scores higher in 1 category and Step 5 Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 35.4.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| QwQ-32B | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 39.8 | 47.9 |
| Released | 2024-11-28 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 36 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
QwQ-32B: 35.4 (#226), Step 5 Preview: 51.8 (#36)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1333 | 1480 |
| Aider Polyglot | 20.9% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 44.6% | — |
| LiveBench Coding | 72.2% | — |
| BigCodeBench Complete | 54.4% | — |
Reasoning Step 5 Preview leads
QwQ-32B: 23.7 (#174), Step 5 Preview: 40.0 (#57)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1325 | 1465 |
| CritPt | — | 20.9% |
| Chess Puzzles | 5% | — |
| LiveBench Reasoning | 83.5% | — |
| LiveBench Data Analysis | 65% | — |
| Epoch Capabilities Index | 137.6 | — |
| ForecastBench | 58.3 | — |
| LiveBench | 72% | — |
Math Step 5 Preview leads
QwQ-32B: 38.0 (#143), Step 5 Preview: 46.1 (#72)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1359 | 1470 |
| OTIS Mock AIME 2024-2025 | 59.2% | — |
| ProofBench | — | 42% |
| LiveBench Math | 77.8% | — |
Knowledge Step 5 Preview leads
QwQ-32B: 37.2 (#158), Step 5 Preview: 41.2 (#112)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1324 | 1470 |
| GPQA Diamond | 65.3% | — |
| Confabulations | 15.6% | — |
Multimodal Not comparable
QwQ-32B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
QwQ-32B: 44.8 (#176), Step 5 Preview: 53.8 (#54)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1305 | 1432 |
| LMArena Chinese | 1378 | 1519 |
| LMArena Russian | 1297 | 1436 |
| LMArena Spanish | 1354 | 1439 |
| LMArena French | 1336 | — |
| LMArena German | 1313 | — |
| LMArena Japanese | 1262 | — |
| LMArena Korean | 1279 | — |
Instruction Following Step 5 Preview leads
QwQ-32B: 72.6 (#137), Step 5 Preview: 76.0 (#50)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1297 | 1444 |
| LiveBench Instruction Following | 81.8% | — |
Long Context QwQ-32B leads
QwQ-32B: 49.0 (#11), Step 5 Preview: 44.5 (#64)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1308 | 1455 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Step 5 Preview leads
QwQ-32B: 50.6 (#180), Step 5 Preview: 62.8 (#71)
| Benchmark | QwQ-32B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1329 | 1442 |
| LMArena Creative Writing | 1288 | 1410 |
| LMArena Multi-Turn | 1314 | 1447 |
| Short-Story Creative Writing | 80.2% | — |
| EQ-Bench Creative Writing | 1257 | — |
| LiveBench Language | 51.4% | — |
Frequently asked questions
Is QwQ-32B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 39.8 on the Noometry Index.
Is QwQ-32B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 35.4 in the Noometry coding category.
How many benchmarks do QwQ-32B and Step 5 Preview share?
13 benchmarks have published results for both models. QwQ-32B has 36 scored results on Noometry and Step 5 Preview has 18.