Model comparison
Qwen3-4B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 19.2.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| Qwen3-4B | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.9 | 47.9 |
| Released | 2025-04-29 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 6 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3-4B: —, Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
Agentic & Tool Use Not comparable
Qwen3-4B: 27.6 (#100), Step 5 Preview: —
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 35.7% | — |
Reasoning Step 5 Preview leads
Qwen3-4B: 19.2 (#268), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | — | 1465 |
Math Step 5 Preview leads
Qwen3-4B: 29.7 (#240), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| MathArena Final-Answer Competitions | 38.5% | — |
| OTIS Mock AIME 2024-2025 | 52.2% | — |
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
Knowledge Step 5 Preview leads
Qwen3-4B: 33.0 (#208), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 52.3% | — |
| Vectara Hallucination Rate | 5.7% | — |
| LMArena Expert | — | 1470 |
Multimodal Not comparable
Qwen3-4B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
Qwen3-4B: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
Qwen3-4B: —, Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
Qwen3-4B: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Qwen3-4B: —, Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen3-4B | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Qwen3-4B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.9 on the Noometry Index.
How many benchmarks do Qwen3-4B and Step 5 Preview share?
0 benchmarks have published results for both models. Qwen3-4B has 6 scored results on Noometry and Step 5 Preview has 18.