Model comparison
Qwen3.6 35B-A3B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.2 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 1 benchmark with published results for both. Qwen3.6 35B-A3B scores higher in 2 categories and Step 3.5 Flash in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 35B-A3B leads 51.4 to 39.0.
- The biggest single-benchmark swing is NYT Connections (extended): 41.6% for Qwen3.6 35B-A3B and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $1.49 for Qwen3.6 35B-A3B.
- Qwen3.6 35B-A3B accepts more context: 262K tokens versus 256K.
Side by side
| Qwen3.6 35B-A3B | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 37.2 | 41.7 |
| Released | 2026-04-01 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 262K | 256K |
| Max output | 66K | 256K |
| Input $ / M tokens | $0.25 | $0.10 |
| Output $ / M tokens | $1.49 | $0.30 |
| Results tracked | 14 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Qwen3.6 35B-A3B: 36.7 (#190), Step 3.5 Flash: 41.7 (#106)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| SciCode | 35.8% | — |
| WeirdML | 34.5% | — |
| LMArena Coding | — | 1436 |
Agentic & Tool Use Not comparable
Qwen3.6 35B-A3B: 21.9 (#126), Step 3.5 Flash: —
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 23% | — |
Reasoning Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 27.2 (#112), Step 3.5 Flash: 21.2 (#202)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 41.6% | 28.4% |
| CritPt | 0.3% | — |
| Chess Puzzles | 26% | — |
| LMArena Hard Prompts | — | 1411 |
| Mystery Game Puzzles | 22% | — |
| DTBench | 73.9% | — |
| LMCA | 29.7% | — |
| Surface Evolver Bench | 44.4% | — |
| Epoch Capabilities Index | 143.92 | — |
Math Step 3.5 Flash leads
Qwen3.6 35B-A3B: 37.9 (#90), Step 3.5 Flash: 40.6 (#77)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20.4% | — |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| LMArena Math | — | 1408 |
Knowledge Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 51.4 (#63), Step 3.5 Flash: 39.0 (#127)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| GPQA Diamond | 84.8% | — |
| LMArena Expert | — | 1422 |
Multilingual Not comparable
Qwen3.6 35B-A3B: —, Step 3.5 Flash: 50.7 (#115)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1386 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1421 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Not comparable
Qwen3.6 35B-A3B: —, Step 3.5 Flash: 73.3 (#119)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |
Long Context Not comparable
Qwen3.6 35B-A3B: —, Step 3.5 Flash: 42.8 (#112)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |
Writing & Preference Not comparable
Qwen3.6 35B-A3B: —, Step 3.5 Flash: 59.0 (#108)
| Benchmark | Qwen3.6 35B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Qwen3.6 35B-A3B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.2 on the Noometry Index.
Which is cheaper, Qwen3.6 35B-A3B or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.6 35B-A3B lists at $0.25 and $1.49.
Is Qwen3.6 35B-A3B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 36.7 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 35B-A3B does, with 262K tokens against 256K.
How many benchmarks do Qwen3.6 35B-A3B and Step 3.5 Flash share?
1 benchmark has published results for both models. Qwen3.6 35B-A3B has 14 scored results on Noometry and Step 3.5 Flash has 19.