Model comparison
Qwen3.5 397B-A17B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 46.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 15 benchmarks with published results for both. Qwen3.5 397B-A17B scores higher in 1 category and Step 5 Preview in 8 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 41.2.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 262K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.5 397B-A17B | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 46.0 | 47.9 |
| Released | 2026-02-01 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.02M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.60 | $1 |
| Output $ / M tokens | $3.60 | $2.70 |
| Results tracked | 36 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen3.5 397B-A17B: 42.0 (#114), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1400 | 1564 |
| LMArena Coding | 1465 | 1480 |
| SciCode | — | 58.9% |
Agentic & Tool Use Not comparable
Qwen3.5 397B-A17B: 33.3 (#53), Step 5 Preview: —
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| APEX-Agents | 24.9% | — |
| τ²-bench Airline | 81.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 84.4% | — |
| τ²-bench Telecom | 97.8% | — |
Reasoning Step 5 Preview leads
Qwen3.5 397B-A17B: 34.5 (#70), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1465 |
| Kagi LLM Benchmark | 73.7% | — |
| NYT Connections (extended) | 58.9% | — |
| CritPt | — | 20.9% |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 65.1% | — |
| Mystery Game Puzzles | 18% | — |
| DTBench | 87.5% | — |
| LMCA | 37.9% | — |
| Epoch Capabilities Index | 146.65 | — |
Math Too close to call
Qwen3.5 397B-A17B: 46.1 (#73), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1454 | 1470 |
| FrontierMath (Tiers 1-3) | 31.2% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | — | 42% |
Knowledge Qwen3.5 397B-A17B leads
Qwen3.5 397B-A17B: 53.3 (#58), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1462 | 1470 |
| GPQA Diamond | 86.4% | — |
Multimodal Too close to call
Qwen3.5 397B-A17B: 40.7 (#44), Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1263 | 1267 |
Multilingual Too close to call
Qwen3.5 397B-A17B: 53.7 (#59), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1430 | 1432 |
| LMArena Chinese | 1500 | 1519 |
| LMArena Russian | 1429 | 1436 |
| LMArena Spanish | 1441 | 1439 |
| LMArena French | 1461 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1426 | — |
| LMArena Korean | 1384 | — |
Instruction Following Too close to call
Qwen3.5 397B-A17B: 75.0 (#77), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1424 | 1444 |
Long Context Too close to call
Qwen3.5 397B-A17B: 44.1 (#74), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1442 | 1455 |
Writing & Preference Too close to call
Qwen3.5 397B-A17B: 62.3 (#79), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen3.5 397B-A17B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1438 | 1442 |
| LMArena Creative Writing | 1401 | 1410 |
| LMArena Multi-Turn | 1446 | 1447 |
| EQ-Bench Creative Writing | 1478 | — |
Frequently asked questions
Is Qwen3.5 397B-A17B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 46.0 on the Noometry Index.
Which is cheaper, Qwen3.5 397B-A17B or Step 5 Preview?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Qwen3.5 397B-A17B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 42.0 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 Qwen3.5 397B-A17B and Step 5 Preview share?
15 benchmarks have published results for both models. Qwen3.5 397B-A17B has 36 scored results on Noometry and Step 5 Preview has 18.