Model comparison
Qwen3.5 Plus vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 42.9 on the Noometry Index. Qwen3.5 Plus costs 1.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 32.8.
- Qwen3.5 Plus is cheaper at $0.40 / $2.40 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 1M.
Side by side
| Qwen3.5 Plus | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 42.9 | 47.9 |
| Released | 2026-02-16 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.02M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.40 | $1 |
| Output $ / M tokens | $2.40 | $2.70 |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3.5 Plus: —, Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
| ALE-Bench | 621.92 | — |
Agentic & Tool Use Not comparable
Qwen3.5 Plus: —, Step 5 Preview: —
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| Vending-Bench 2 | 0.54 | — |
Reasoning Step 5 Preview leads
Qwen3.5 Plus: 32.8 (#74), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| Chess Puzzles | 22% | — |
| LMArena Hard Prompts | — | 1465 |
| Mystery Game Puzzles | 17% | — |
| DTBench | 80.5% | — |
| LMCA | 36.4% | — |
| Epoch Capabilities Index | 146.78 | — |
Math Qwen3.5 Plus leads
Qwen3.5 Plus: 49.6 (#61), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
| FrontierMath (Feb 2025 set) | 21% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.5 Plus leads
Qwen3.5 Plus: 46.0 (#83), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 84.8% | — |
| SimpleQA Verified | 25.4% | — |
| Vectara Hallucination Rate | 10.7% | — |
| LMArena Expert | — | 1470 |
Multimodal Not comparable
Qwen3.5 Plus: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
Qwen3.5 Plus: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
Qwen3.5 Plus: —, Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Step 5 Preview leads
Qwen3.5 Plus: 43.0 (#113), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| CL-bench | 19.8% | — |
| CL-bench Life | 12.4% | — |
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Qwen3.5 Plus: —, Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen3.5 Plus | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Qwen3.5 Plus better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 42.9 on the Noometry Index. Qwen3.5 Plus costs 1.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Qwen3.5 Plus or Step 5 Preview?
Qwen3.5 Plus is cheaper. It lists at $0.40 per million input tokens and $2.40 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 1M.
How many benchmarks do Qwen3.5 Plus and Step 5 Preview share?
0 benchmarks have published results for both models. Qwen3.5 Plus has 15 scored results on Noometry and Step 5 Preview has 18.