Model comparison
Qwen3.7 Max vs Step 3.7 Flash
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 9.0× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 4 benchmarks with published results for both. Qwen3.7 Max 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 Qwen3.7 Max leads 49.2 to 21.6.
- The biggest single-benchmark swing is NYT Connections (extended): 85.1% for Qwen3.7 Max 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 $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 256K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.
Side by side
| Qwen3.7 Max | Step 3.7 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 51.5 | 37.3 |
| Released | 2026-05-19 | 2026-05-29 |
| Weights | Proprietary | Open |
| Context window | 1M | 256K |
| Max output | 131K | 256K |
| Input $ / M tokens | $2.50 | $0.18 |
| Output $ / M tokens | $7.50 | $1.11 |
| Results tracked | 33 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Qwen3.7 Max: 50.4 (#45), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| SciCode | 48.8% | 40% |
| ALE-Bench | 1,189 | 694.12 |
| SWE-bench Verified | 77.3% | — |
| LMArena WebDev | 1515 | — |
| LMArena Coding | 1498 | — |
Agentic & Tool Use Not comparable
Qwen3.7 Max: 22.1 (#135), Step 3.7 Flash: —
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| GBAEval | 0.4% | — |
Reasoning Qwen3.7 Max leads
Qwen3.7 Max: 49.2 (#38), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | 85.1% | 39.7% |
| CritPt | 13.4% | 2.3% |
| SimpleBench | 70.4% | — |
| Chess Puzzles | 19% | — |
| EBR-Bench | 9.5% | — |
| LMArena Hard Prompts | 1483 | — |
| Mystery Game Puzzles | 32% | — |
| DTBench | 92.3% | — |
| LMCA | 44% | — |
| Epoch Capabilities Index | 153.68 | — |
Math Qwen3.7 Max leads
Qwen3.7 Max: 62.4 (#32), Step 3.7 Flash: 42.9 (#82)
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 34.1% | — |
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| LMArena Math | 1490 | — |
Knowledge Not comparable
Qwen3.7 Max: 61.6 (#28), Step 3.7 Flash: —
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 55.8% | — |
| LMArena Expert | 1488 | — |
Multilingual Not comparable
Qwen3.7 Max: 56.9 (#15), Step 3.7 Flash: —
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1530 | — |
| LMArena Russian | 1484 | — |
Instruction Following Not comparable
Qwen3.7 Max: 76.7 (#38), Step 3.7 Flash: —
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1460 | — |
Long Context Not comparable
Qwen3.7 Max: 45.4 (#40), Step 3.7 Flash: —
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1482 | — |
Writing & Preference Not comparable
Qwen3.7 Max: 65.0 (#54), Step 3.7 Flash: —
| Benchmark | Qwen3.7 Max | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1476 | — |
| LMArena Creative Writing | 1449 | — |
| EQ-Bench 4 | 1110 | — |
| LMArena Multi-Turn | 1481 | — |
Frequently asked questions
Is Qwen3.7 Max better than Step 3.7 Flash?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 9.0× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3.7 Max 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; Qwen3.7 Max lists at $2.50 and $7.50.
Is Qwen3.7 Max or Step 3.7 Flash better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 40.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 256K.
How many benchmarks do Qwen3.7 Max and Step 3.7 Flash share?
4 benchmarks have published results for both models. Qwen3.7 Max has 33 scored results on Noometry and Step 3.7 Flash has 5.