Model comparison
Qwen3.8 Max vs Step 3.5 Flash
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 42.3 on the Noometry Index. Step 3.5 Flash costs 20× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 18 benchmarks with published results for both. Qwen3.8 Max scores higher in 8 categories and Step 3.5 Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 Max leads 54.4 to 22.2.
- The biggest single-benchmark swing is NYT Connections (extended): 88.3% for Qwen3.8 Max and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 256K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| Qwen3.8 Max | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 56.8 | 42.3 |
| Released | 2026-08-02 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | 1M | 256K |
| Max output | 131K | 256K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $6 | $0.30 |
| Results tracked | 39 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen3.8 Max: 53.5 (#29), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1502 | 1436 |
| DeepSWE | 57.5% | — |
| LMArena WebDev | 1674 | — |
| FrontierSWE | 17.8% | — |
| SciCode | 53.2% | — |
Agentic & Tool Use Not comparable
Qwen3.8 Max: 45.4 (#14), Step 3.5 Flash: —
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| APEX-Agents | 63.3% | — |
| τ²-bench Banking | 55.1% | — |
| GDP.pdf | 23.2% | — |
Reasoning Qwen3.8 Max leads
Qwen3.8 Max: 54.4 (#26), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 88.3% | 28.4% |
| LMArena Hard Prompts | 1496 | 1411 |
| CritPt | 20% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 38% | — |
| DTBench | 92% | — |
| LMCA | 46.2% | — |
| Epoch Capabilities Index | 156.41 | — |
Math Qwen3.8 Max leads
Qwen3.8 Max: 73.2 (#20), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1499 | 1408 |
| FrontierMath (Tiers 1-3) | 74.7% | — |
| FrontierMath Tier 4 | 46.3% | — |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 58% | — |
Knowledge Qwen3.8 Max leads
Qwen3.8 Max: 61.7 (#27), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1507 | 1421 |
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 47.3% | — |
Multimodal Not comparable
Qwen3.8 Max: 37.2 (#75), Step 3.5 Flash: —
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 20% | — |
Multilingual Qwen3.8 Max leads
Qwen3.8 Max: 56.7 (#18), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1472 | 1385 |
| LMArena Chinese | 1538 | 1447 |
| LMArena French | 1503 | 1421 |
| LMArena German | 1483 | 1405 |
| LMArena Japanese | 1467 | 1354 |
| LMArena Korean | 1461 | 1352 |
| LMArena Russian | 1481 | 1385 |
| LMArena Spanish | 1492 | 1419 |
Instruction Following Qwen3.8 Max leads
Qwen3.8 Max: 77.6 (#17), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1479 | 1385 |
Long Context Qwen3.8 Max leads
Qwen3.8 Max: 45.6 (#31), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1489 | 1402 |
Writing & Preference Qwen3.8 Max leads
Qwen3.8 Max: 67.1 (#30), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Qwen3.8 Max | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1483 | 1403 |
| LMArena Creative Writing | 1479 | 1357 |
| LMArena Multi-Turn | 1489 | 1405 |
Frequently asked questions
Is Qwen3.8 Max better than Step 3.5 Flash?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 42.3 on the Noometry Index. Step 3.5 Flash costs 20× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3.8 Max or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Qwen3.8 Max or Step 3.5 Flash better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 256K.
How many benchmarks do Qwen3.8 Max and Step 3.5 Flash share?
18 benchmarks have published results for both models. Qwen3.8 Max has 39 scored results on Noometry and Step 3.5 Flash has 19.