Model comparison
Qwen3.5 35B-A3B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 2.1× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 16 benchmarks with published results for both. Qwen3.5 35B-A3B scores higher in 1 category and Step 5 Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 33.8.
- The biggest single-benchmark swing is SciCode: 29.3% for Qwen3.5 35B-A3B and 58.9% for Step 5 Preview.
- Qwen3.5 35B-A3B is cheaper at $0.25 / $2 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 35B-A3B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.5 35B-A3B | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 42.0 | 47.9 |
| Released | 2026-02-01 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.02M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.25 | $1 |
| Output $ / M tokens | $2 | $2.70 |
| Results tracked | 28 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen3.5 35B-A3B: 33.8 (#251), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1254 | 1564 |
| SciCode | 29.3% | 58.9% |
| LMArena Coding | 1410 | 1480 |
Reasoning Step 5 Preview leads
Qwen3.5 35B-A3B: 24.6 (#161), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| CritPt | 0.6% | 20.9% |
| LMArena Hard Prompts | 1400 | 1465 |
| Chess Puzzles | 10% | — |
| DTBench | 80% | — |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | 142.52 | — |
Math Step 5 Preview leads
Qwen3.5 35B-A3B: 39.9 (#97), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1404 | 1470 |
| MathArena Final-Answer Competitions | 56% | — |
| OTIS Mock AIME 2024-2025 | 70% | — |
| ProofBench | — | 42% |
Knowledge Qwen3.5 35B-A3B leads
Qwen3.5 35B-A3B: 47.8 (#79), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1408 | 1470 |
| GPQA Diamond | 83.5% | — |
| Vectara Hallucination Rate | 10.5% | — |
Multimodal Not comparable
Qwen3.5 35B-A3B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Qwen3.5 35B-A3B: 50.0 (#127), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1378 | 1432 |
| LMArena Chinese | 1457 | 1519 |
| LMArena Russian | 1376 | 1436 |
| LMArena Spanish | 1392 | 1439 |
| LMArena French | 1412 | — |
| LMArena German | 1367 | — |
| LMArena Japanese | 1325 | — |
| LMArena Korean | 1356 | — |
Instruction Following Step 5 Preview leads
Qwen3.5 35B-A3B: 72.8 (#128), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1379 | 1444 |
Long Context Step 5 Preview leads
Qwen3.5 35B-A3B: 42.4 (#127), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1389 | 1455 |
Writing & Preference Step 5 Preview leads
Qwen3.5 35B-A3B: 57.9 (#124), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen3.5 35B-A3B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1395 | 1442 |
| LMArena Creative Writing | 1346 | 1410 |
| LMArena Multi-Turn | 1390 | 1447 |
Frequently asked questions
Is Qwen3.5 35B-A3B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 2.1× 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 35B-A3B or Step 5 Preview?
Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Qwen3.5 35B-A3B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 33.8 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 35B-A3B and Step 5 Preview share?
16 benchmarks have published results for both models. Qwen3.5 35B-A3B has 28 scored results on Noometry and Step 5 Preview has 18.