Model comparison
Qwen3.6 Max Preview vs Step 3.7 Flash
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 7.0× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 1 benchmark with published results for both. Qwen3.6 Max Preview scores higher in 3 categories and Step 3.7 Flash in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 Max Preview leads 41.7 to 21.6.
- The biggest single-benchmark swing is NYT Connections (extended): 74.1% for Qwen3.6 Max Preview and 39.7% for Step 3.7 Flash.
- Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 256K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.
Side by side
| Qwen3.6 Max Preview | Step 3.7 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 51.5 | 37.3 |
| Released | 2026-04-20 | 2026-05-29 |
| Weights | Proprietary | Open |
| Context window | 262K | 256K |
| Max output | 66K | 256K |
| Input $ / M tokens | $1.30 | $0.18 |
| Output $ / M tokens | $7.80 | $1.11 |
| Results tracked | 29 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 48.7 (#54), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | — | 40% |
| LMArena Coding | 1471 | — |
| ALE-Bench | — | 694.12 |
Agentic & Tool Use Not comparable
Qwen3.6 Max Preview: —, Step 3.7 Flash: —
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| Vending-Bench 2 | 4,254 | — |
Reasoning Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 41.7 (#53), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | 74.1% | 39.7% |
| SimpleBench | 63% | — |
| CritPt | — | 2.3% |
| Chess Puzzles | 20% | — |
| LMArena Hard Prompts | 1457 | — |
| 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 3.7 Flash: 42.9 (#82)
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| LMArena Math | 1465 | — |
| FrontierMath (Feb 2025 set) | 23.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Not comparable
Qwen3.6 Max Preview: 57.6 (#39), Step 3.7 Flash: —
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 52% | — |
| LMArena Expert | 1478 | — |
Multilingual Not comparable
Qwen3.6 Max Preview: 54.2 (#48), Step 3.7 Flash: —
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1437 | — |
| LMArena Chinese | 1487 | — |
| LMArena French | 1449 | — |
| LMArena Russian | 1445 | — |
| LMArena Spanish | 1454 | — |
Instruction Following Not comparable
Qwen3.6 Max Preview: 75.7 (#55), Step 3.7 Flash: —
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1438 | — |
Long Context Not comparable
Qwen3.6 Max Preview: 44.6 (#61), Step 3.7 Flash: —
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1457 | — |
Writing & Preference Not comparable
Qwen3.6 Max Preview: 63.8 (#60), Step 3.7 Flash: —
| Benchmark | Qwen3.6 Max Preview | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1447 | — |
| LMArena Creative Writing | 1435 | — |
| LMArena Multi-Turn | 1456 | — |
Frequently asked questions
Is Qwen3.6 Max Preview better than Step 3.7 Flash?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 7.0× 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 3.7 Flash?
Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Qwen3.6 Max Preview or Step 3.7 Flash better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 40.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 256K.
How many benchmarks do Qwen3.6 Max Preview and Step 3.7 Flash share?
1 benchmark has published results for both models. Qwen3.6 Max Preview has 29 scored results on Noometry and Step 3.7 Flash has 5.