Model comparison
Qwen Max vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 34.7 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 13 benchmarks with published results for both. Qwen Max scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 22.3.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Step 5 Preview accepts more context: 1.02M tokens versus 33K.
Side by side
| Qwen Max | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 34.7 | 47.9 |
| Released | 2024-04-03 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 33K | 1.02M |
| Max output | 8K | 66K |
| Input $ / M tokens | $1.60 | $1 |
| Output $ / M tokens | $6.40 | $2.70 |
| Results tracked | 23 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen Max: 30.7 (#292), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1288 | 1480 |
| Aider Polyglot | 21.8% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Qwen Max: 25.1 (#151), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1465 |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
Qwen Max: 22.3 (#276), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Math | 1275 | 1470 |
| OTIS Mock AIME 2024-2025 | 16.1% | — |
| ProofBench | — | 42% |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Step 5 Preview leads
Qwen Max: 30.3 (#228), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1248 | 1470 |
| GPQA Diamond | 56.1% | — |
Multimodal Not comparable
Qwen Max: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Qwen Max: 41.8 (#202), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1263 | 1432 |
| LMArena Chinese | 1254 | 1519 |
| LMArena Russian | 1274 | 1436 |
| LMArena Spanish | 1290 | 1439 |
| LMArena French | 1330 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1205 | — |
| LMArena Korean | 1142 | — |
Instruction Following Step 5 Preview leads
Qwen Max: 66.5 (#208), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1262 | 1444 |
Long Context Step 5 Preview leads
Qwen Max: 39.4 (#180), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1288 | 1455 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Step 5 Preview leads
Qwen Max: 47.8 (#205), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen Max | Step 5 Preview |
|---|---|---|
| LMArena Text | 1282 | 1442 |
| LMArena Creative Writing | 1248 | 1410 |
| LMArena Multi-Turn | 1277 | 1447 |
Frequently asked questions
Is Qwen Max better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 34.7 on the Noometry Index.
Which is cheaper, Qwen Max or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Qwen Max or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 33K.
How many benchmarks do Qwen Max and Step 5 Preview share?
13 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Step 5 Preview has 18.