Model comparison
Qwen3.6 Max Preview vs Step 5 Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 47.9 on the Noometry Index. Step 5 Preview costs 2.1× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 14 benchmarks with published results for both. Qwen3.6 Max Preview scores higher in 6 categories and Step 5 Preview in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Max Preview leads 57.6 to 41.2.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 262K.
Side by side
| Qwen3.6 Max Preview | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 51.5 | 47.9 |
| Released | 2026-04-20 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 262K | 1.02M |
| Max output | 66K | 66K |
| Input $ / M tokens | $1.30 | $1 |
| Output $ / M tokens | $7.80 | $2.70 |
| Results tracked | 29 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen3.6 Max Preview: 48.7 (#54), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1482 | 1564 |
| LMArena Coding | 1471 | 1480 |
| SWE-bench Verified | 76.7% | — |
| SciCode | — | 58.9% |
Agentic & Tool Use Not comparable
Qwen3.6 Max Preview: —, Step 5 Preview: —
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| Vending-Bench 2 | 4,254 | — |
Reasoning Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 41.7 (#53), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1465 |
| SimpleBench | 63% | — |
| NYT Connections (extended) | 74.1% | — |
| CritPt | — | 20.9% |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 87.2% | — |
| LMCA | 42.5% | — |
| Epoch Capabilities Index | 149.24 | — |
Math Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 54.1 (#46), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Math | 1465 | 1470 |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | — | 42% |
| FrontierMath (Feb 2025 set) | 23.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 57.6 (#39), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1478 | 1470 |
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 52% | — |
Multimodal Not comparable
Qwen3.6 Max Preview: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Too close to call
Qwen3.6 Max Preview: 54.2 (#48), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1437 | 1432 |
| LMArena Chinese | 1487 | 1519 |
| LMArena Russian | 1445 | 1436 |
| LMArena Spanish | 1454 | 1439 |
| LMArena French | 1449 | — |
Instruction Following Too close to call
Qwen3.6 Max Preview: 75.7 (#55), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1438 | 1444 |
Long Context Too close to call
Qwen3.6 Max Preview: 44.6 (#61), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1457 | 1455 |
Writing & Preference Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 63.8 (#60), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen3.6 Max Preview | Step 5 Preview |
|---|---|---|
| LMArena Text | 1447 | 1442 |
| LMArena Creative Writing | 1435 | 1410 |
| LMArena Multi-Turn | 1456 | 1447 |
Frequently asked questions
Is Qwen3.6 Max Preview better than Step 5 Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 47.9 on the Noometry Index. Step 5 Preview costs 2.1× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Qwen3.6 Max Preview or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Qwen3.6 Max Preview or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 48.7 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 262K.
How many benchmarks do Qwen3.6 Max Preview and Step 5 Preview share?
14 benchmarks have published results for both models. Qwen3.6 Max Preview has 29 scored results on Noometry and Step 5 Preview has 18.