Model comparison
Qwen Plus vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 37.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 13 benchmarks with published results for both. Qwen Plus scores higher in 0 categories and Step 3 in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 37.6 to 23.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Qwen Plus | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 37.1 | 40.5 |
| Released | 2024-01-25 | — |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 20 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen Plus: 38.9 (#167), Step 3: 40.1 (#147)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Coding | 1328 | 1367 |
Reasoning Too close to call
Qwen Plus: 28.4 (#107), Step 3: 28.4 (#105)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 63.3% | 62.3% |
| LMArena Hard Prompts | 1317 | 1355 |
| DTBench | 81.1% | — |
| LMCA | 24% | — |
Math Step 3 leads
Qwen Plus: 23.3 (#271), Step 3: 37.6 (#148)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Math | 1326 | 1366 |
| OTIS Mock AIME 2024-2025 | 17.8% | — |
| MATH Level 5 | 65.3% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Step 3 leads
Qwen Plus: 27.4 (#251), Step 3: 36.8 (#164)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Expert | 1328 | 1333 |
| GPQA Diamond | 48.1% | — |
Multimodal Not comparable
Qwen Plus: —, Step 3: 35.5 (#86)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Qwen Plus: 45.1 (#175), Step 3: 46.3 (#159)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Non-English | 1310 | 1327 |
| LMArena Chinese | 1347 | 1397 |
| LMArena Russian | 1323 | 1331 |
| LMArena German | — | 1371 |
| LMArena Japanese | 1251 | — |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Qwen Plus: 68.8 (#181), Step 3: 70.4 (#164)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1303 | 1332 |
Long Context Too close to call
Qwen Plus: 40.3 (#158), Step 3: 40.3 (#157)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Longer Query | 1324 | 1326 |
Writing & Preference Step 3 leads
Qwen Plus: 52.2 (#176), Step 3: 54.3 (#151)
| Benchmark | Qwen Plus | Step 3 |
|---|---|---|
| LMArena Text | 1326 | 1350 |
| LMArena Creative Writing | 1293 | 1321 |
| LMArena Multi-Turn | 1336 | 1341 |
Frequently asked questions
Is Qwen Plus better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 37.1 on the Noometry Index.
Is Qwen Plus or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 38.9 in the Noometry coding category.
How many benchmarks do Qwen Plus and Step 3 share?
13 benchmarks have published results for both models. Qwen Plus has 20 scored results on Noometry and Step 3 has 17.