Model comparison
Qwen3.5-Flash vs Step 3
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 40.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 15 benchmarks with published results for both. Qwen3.5-Flash scores higher in 6 categories and Step 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-Flash leads 43.2 to 36.8.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Qwen3.5-Flash | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 42.5 | 40.5 |
| Released | 2026-02-23 | — |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen3.5-Flash: 34.2 (#242), Step 3: 40.1 (#147)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Coding | 1412 | 1367 |
| LMArena WebDev | 1244 | — |
| ALE-Bench | 221.8 | — |
Agentic & Tool Use Not comparable
Qwen3.5-Flash: —, Step 3: —
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| Vending-Bench 2 | 462.69 | — |
Reasoning Qwen3.5-Flash leads
Qwen3.5-Flash: 33.7 (#72), Step 3: 28.4 (#105)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 21% | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 82.9% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 143.98 | — |
Math Too close to call
Qwen3.5-Flash: 37.4 (#158), Step 3: 37.6 (#148)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Math | 1407 | 1366 |
| FrontierMath (Tiers 1-3) | 18.2% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 6.2% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.5-Flash leads
Qwen3.5-Flash: 43.2 (#93), Step 3: 36.8 (#164)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Expert | 1407 | 1333 |
| GPQA Diamond | 82.3% | — |
| SimpleQA Verified | 20.3% | — |
| Vectara Hallucination Rate | 10.5% | — |
Multimodal Not comparable
Qwen3.5-Flash: —, Step 3: 35.5 (#86)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Qwen3.5-Flash leads
Qwen3.5-Flash: 50.5 (#121), Step 3: 46.3 (#159)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Non-English | 1385 | 1327 |
| LMArena Chinese | 1446 | 1397 |
| LMArena German | 1390 | 1371 |
| LMArena Korean | 1344 | 1269 |
| LMArena Russian | 1379 | 1331 |
| LMArena Spanish | 1400 | 1371 |
| LMArena French | 1412 | — |
| LMArena Japanese | 1368 | — |
Instruction Following Qwen3.5-Flash leads
Qwen3.5-Flash: 72.6 (#139), Step 3: 70.4 (#164)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1374 | 1332 |
Long Context Qwen3.5-Flash leads
Qwen3.5-Flash: 42.4 (#124), Step 3: 40.3 (#157)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Longer Query | 1392 | 1326 |
Writing & Preference Qwen3.5-Flash leads
Qwen3.5-Flash: 57.9 (#122), Step 3: 54.3 (#151)
| Benchmark | Qwen3.5-Flash | Step 3 |
|---|---|---|
| LMArena Text | 1397 | 1350 |
| LMArena Creative Writing | 1343 | 1321 |
| LMArena Multi-Turn | 1393 | 1341 |
Frequently asked questions
Is Qwen3.5-Flash better than Step 3?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 40.5 on the Noometry Index.
Is Qwen3.5-Flash or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 34.2 in the Noometry coding category.
How many benchmarks do Qwen3.5-Flash and Step 3 share?
15 benchmarks have published results for both models. Qwen3.5-Flash has 32 scored results on Noometry and Step 3 has 17.