Model comparison
QwQ-32B vs Step 3
QwQ-32B and Step 3 score almost the same on the Noometry Index (39.8 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 15 benchmarks with published results for both. QwQ-32B scores higher in 4 categories and Step 3 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where QwQ-32B leads 49.0 to 40.3.
Side by side
| QwQ-32B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 39.8 | 40.5 |
| Released | 2024-11-28 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 36 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
QwQ-32B: 35.4 (#226), Step 3: 40.1 (#147)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Coding | 1333 | 1367 |
| Aider Polyglot | 20.9% | — |
| BigCodeBench Instruct | 44.6% | — |
| LiveBench Coding | 72.2% | — |
| BigCodeBench Complete | 54.4% | — |
Reasoning Step 3 leads
QwQ-32B: 23.7 (#174), Step 3: 28.4 (#105)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1325 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 5% | — |
| LiveBench Reasoning | 83.5% | — |
| LiveBench Data Analysis | 65% | — |
| Epoch Capabilities Index | 137.6 | — |
| ForecastBench | 58.3 | — |
| LiveBench | 72% | — |
Math Too close to call
QwQ-32B: 38.0 (#143), Step 3: 37.6 (#148)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Math | 1359 | 1366 |
| OTIS Mock AIME 2024-2025 | 59.2% | — |
| LiveBench Math | 77.8% | — |
Knowledge Too close to call
QwQ-32B: 37.2 (#158), Step 3: 36.8 (#164)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Expert | 1324 | 1333 |
| GPQA Diamond | 65.3% | — |
| Confabulations | 15.6% | — |
Multimodal Not comparable
QwQ-32B: —, Step 3: 35.5 (#86)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
QwQ-32B: 44.8 (#176), Step 3: 46.3 (#159)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Non-English | 1305 | 1327 |
| LMArena Chinese | 1378 | 1397 |
| LMArena German | 1313 | 1371 |
| LMArena Korean | 1279 | 1269 |
| LMArena Russian | 1297 | 1331 |
| LMArena Spanish | 1354 | 1371 |
| LMArena French | 1336 | — |
| LMArena Japanese | 1262 | — |
Instruction Following QwQ-32B leads
QwQ-32B: 72.6 (#137), Step 3: 70.4 (#164)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1332 |
| LiveBench Instruction Following | 81.8% | — |
Long Context QwQ-32B leads
QwQ-32B: 49.0 (#11), Step 3: 40.3 (#157)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1308 | 1326 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Step 3 leads
QwQ-32B: 50.6 (#180), Step 3: 54.3 (#151)
| Benchmark | QwQ-32B | Step 3 |
|---|---|---|
| LMArena Text | 1329 | 1350 |
| LMArena Creative Writing | 1288 | 1321 |
| LMArena Multi-Turn | 1314 | 1341 |
| 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?
QwQ-32B and Step 3 score almost the same on the Noometry Index (39.8 vs 40.5), so choose on price, context window or the category you care about most.
Is QwQ-32B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 35.4 in the Noometry coding category.
How many benchmarks do QwQ-32B and Step 3 share?
15 benchmarks have published results for both models. QwQ-32B has 36 scored results on Noometry and Step 3 has 17.