Model comparison
Qwen3-4B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 1 benchmark with published results for both. Qwen3-4B scores higher in 0 categories and Step 3.5 Flash in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 42.6 to 29.7.
- The biggest single-benchmark swing is MathArena Final-Answer Competitions: 38.5% for Qwen3-4B and 66.8% for Step 3.5 Flash.
Side by side
| Qwen3-4B | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.9 | 42.3 |
| Released | 2025-04-29 | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 6 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3-4B: —, Step 3.5 Flash: 42.4 (#105)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | — | 1436 |
Agentic & Tool Use Not comparable
Qwen3-4B: 27.6 (#100), Step 3.5 Flash: —
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 35.7% | — |
Reasoning Step 3.5 Flash leads
Qwen3-4B: 19.2 (#268), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | — | 28.4% |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | — | 1411 |
Math Step 3.5 Flash leads
Qwen3-4B: 29.7 (#240), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 38.5% | 66.8% |
| OTIS Mock AIME 2024-2025 | 52.2% | — |
| LMArena Math | — | 1408 |
Knowledge Step 3.5 Flash leads
Qwen3-4B: 33.0 (#208), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| GPQA Diamond | 52.3% | — |
| Vectara Hallucination Rate | 5.7% | — |
| LMArena Expert | — | 1421 |
Multilingual Not comparable
Qwen3-4B: —, Step 3.5 Flash: 50.5 (#119)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Not comparable
Qwen3-4B: —, Step 3.5 Flash: 73.1 (#124)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |
Long Context Not comparable
Qwen3-4B: —, Step 3.5 Flash: 42.8 (#117)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |
Writing & Preference Not comparable
Qwen3-4B: —, Step 3.5 Flash: 58.8 (#113)
| Benchmark | Qwen3-4B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Qwen3-4B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.9 on the Noometry Index.
How many benchmarks do Qwen3-4B and Step 3.5 Flash share?
1 benchmark has published results for both models. Qwen3-4B has 6 scored results on Noometry and Step 3.5 Flash has 19.