Model comparison
Qwen3.6 35B-A3B vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 37.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in knowledge, where Qwen3.6 35B-A3B leads 51.4 to 36.2.
Side by side
| Qwen3.6 35B-A3B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 37.2 | 39.9 |
| Released | 2026-04-01 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $1.49 | — |
| Results tracked | 14 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen3.6 35B-A3B: 36.7 (#190), Step 3: 39.5 (#144)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| SciCode | 35.8% | — |
| WeirdML | 34.5% | — |
| LMArena Coding | — | 1367 |
Agentic & Tool Use Not comparable
Qwen3.6 35B-A3B: 21.9 (#126), Step 3: —
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| Terminal-Bench | 23% | — |
Reasoning Too close to call
Qwen3.6 35B-A3B: 27.2 (#112), Step 3: 27.6 (#102)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 41.6% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 26% | — |
| LMArena Hard Prompts | — | 1355 |
| Mystery Game Puzzles | 22% | — |
| DTBench | 73.9% | — |
| LMCA | 29.7% | — |
| Surface Evolver Bench | 44.4% | — |
| Epoch Capabilities Index | 143.92 | — |
Math Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 37.9 (#90), Step 3: 34.9 (#148)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20.4% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| LMArena Math | — | 1366 |
Knowledge Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 51.4 (#63), Step 3: 36.2 (#161)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| GPQA Diamond | 84.8% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Qwen3.6 35B-A3B: —, Step 3: 34.9 (#81)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
Qwen3.6 35B-A3B: —, Step 3: 46.5 (#154)
| Benchmark | Qwen3.6 35B-A3B | 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 35B-A3B: —, Step 3: 70.6 (#159)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Qwen3.6 35B-A3B: —, Step 3: 40.3 (#152)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Qwen3.6 35B-A3B: —, Step 3: 54.5 (#146)
| Benchmark | Qwen3.6 35B-A3B | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is Qwen3.6 35B-A3B better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 37.2 on the Noometry Index.
Is Qwen3.6 35B-A3B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 36.7 in the Noometry coding category.
How many benchmarks do Qwen3.6 35B-A3B and Step 3 share?
0 benchmarks have published results for both models. Qwen3.6 35B-A3B has 14 scored results on Noometry and Step 3 has 17.