Model comparison
Qwen3.6 Flash vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 38.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in knowledge, where Qwen3.6 Flash leads 42.1 to 36.8.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Qwen3.6 Flash | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 38.8 | 40.5 |
| Released | 2026-04-27 | — |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $1.13 | — |
| Results tracked | 13 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3.6 Flash: —, Step 3: 40.1 (#147)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |
| ALE-Bench | 326.4 | — |
Reasoning Too close to call
Qwen3.6 Flash: 29.0 (#96), Step 3: 28.4 (#105)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| SimpleBench | 35.2% | — |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 20% | — |
| LMArena Hard Prompts | — | 1355 |
| Mystery Game Puzzles | 18% | — |
| DTBench | 77.1% | — |
| LMCA | 31% | — |
| Epoch Capabilities Index | 143.26 | — |
Math Qwen3.6 Flash leads
Qwen3.6 Flash: 39.0 (#117), Step 3: 37.6 (#148)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 22.5% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| LMArena Math | — | 1366 |
| FrontierMath (Feb 2025 set) | 10.3% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3.6 Flash leads
Qwen3.6 Flash: 42.1 (#100), Step 3: 36.8 (#164)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| GPQA Diamond | 83.3% | — |
| SimpleQA Verified | 15.9% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Qwen3.6 Flash: —, Step 3: 35.5 (#86)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Not comparable
Qwen3.6 Flash: —, Step 3: 46.3 (#159)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |
Instruction Following Not comparable
Qwen3.6 Flash: —, Step 3: 70.4 (#164)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Qwen3.6 Flash: —, Step 3: 40.3 (#157)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Qwen3.6 Flash: —, Step 3: 54.3 (#151)
| Benchmark | Qwen3.6 Flash | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is Qwen3.6 Flash better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 38.8 on the Noometry Index.
How many benchmarks do Qwen3.6 Flash and Step 3 share?
0 benchmarks have published results for both models. Qwen3.6 Flash has 13 scored results on Noometry and Step 3 has 17.