Model comparison
Qwen2.5-Max vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 40.7 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 13 benchmarks with published results for both. Qwen2.5-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 reasoning, where Step 5 Preview leads 40.0 to 25.6.
Side by side
| Qwen2.5-Max | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 40.7 | 47.9 |
| Released | 2025-01-25 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 27 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen2.5-Max: 41.8 (#117), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1359 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LiveBench Coding | 64.4% | — |
Reasoning Step 5 Preview leads
Qwen2.5-Max: 25.6 (#147), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1465 |
| CritPt | — | 20.9% |
| LiveBench Reasoning | 51.4% | — |
| LiveBench Data Analysis | 67.9% | — |
| Epoch Capabilities Index | 132.53 | — |
| LiveBench | 62.3% | — |
Math Step 5 Preview leads
Qwen2.5-Max: 36.9 (#162), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Math | 1369 | 1470 |
| ProofBench | — | 42% |
| LiveBench Math | 58.4% | — |
Knowledge Step 5 Preview leads
Qwen2.5-Max: 35.3 (#186), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1337 | 1470 |
| Confabulations | 21.8% | — |
Multimodal Not comparable
Qwen2.5-Max: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Qwen2.5-Max: 48.1 (#146), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1352 | 1432 |
| LMArena Chinese | 1382 | 1519 |
| LMArena Russian | 1353 | 1436 |
| LMArena Spanish | 1377 | 1439 |
| LMArena French | 1396 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1300 | — |
| LMArena Korean | 1304 | — |
Instruction Following Step 5 Preview leads
Qwen2.5-Max: 71.3 (#152), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1335 | 1444 |
| LiveBench Instruction Following | 75.3% | — |
Long Context Step 5 Preview leads
Qwen2.5-Max: 41.4 (#142), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1358 | 1455 |
Writing & Preference Step 5 Preview leads
Qwen2.5-Max: 55.4 (#146), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen2.5-Max | Step 5 Preview |
|---|---|---|
| LMArena Text | 1367 | 1442 |
| LMArena Creative Writing | 1339 | 1410 |
| LMArena Multi-Turn | 1364 | 1447 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |
Frequently asked questions
Is Qwen2.5-Max better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 40.7 on the Noometry Index.
Is Qwen2.5-Max or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 41.8 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Step 5 Preview share?
13 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Step 5 Preview has 18.