Model comparison
Qwen3.6 27B vs Step 3
Qwen3.6 27B is the stronger model overall, scoring 41.9 to 39.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in knowledge, where Qwen3.6 27B leads 52.4 to 36.2.
Side by side
| Qwen3.6 27B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 41.9 | 39.9 |
| Released | 2026-04-22 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $3.60 | — |
| Results tracked | 11 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen3.6 27B: 38.5 (#162), Step 3: 39.5 (#144)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| SciCode | 37.3% | — |
| LMArena Coding | — | 1367 |
Reasoning Step 3 leads
Qwen3.6 27B: 24.4 (#148), Step 3: 27.6 (#102)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 0.9% | — |
| Chess Puzzles | 22% | — |
| LMArena Hard Prompts | — | 1355 |
| Mystery Game Puzzles | 7% | — |
| DTBench | 78.1% | — |
| LMCA | 34.5% | — |
| Epoch Capabilities Index | 146.47 | — |
Math Qwen3.6 27B leads
Qwen3.6 27B: 47.5 (#56), Step 3: 34.9 (#148)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 35.1% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| LMArena Math | — | 1366 |
Knowledge Qwen3.6 27B leads
Qwen3.6 27B: 52.4 (#58), Step 3: 36.2 (#161)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| GPQA Diamond | 85.9% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Qwen3.6 27B: —, Step 3: 34.9 (#81)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
Qwen3.6 27B: —, Step 3: 46.5 (#154)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Not comparable
Qwen3.6 27B: —, Step 3: 70.6 (#159)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Qwen3.6 27B: —, Step 3: 40.3 (#152)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Step 3 leads
Qwen3.6 27B: 50.3 (#180), Step 3: 54.5 (#146)
| Benchmark | Qwen3.6 27B | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| EQ-Bench 4 | 1026 | — |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is Qwen3.6 27B better than Step 3?
Qwen3.6 27B is the stronger model overall, scoring 41.9 to 39.9 on the Noometry Index.
Is Qwen3.6 27B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 38.5 in the Noometry coding category.
How many benchmarks do Qwen3.6 27B and Step 3 share?
0 benchmarks have published results for both models. Qwen3.6 27B has 11 scored results on Noometry and Step 3 has 17.