Model comparison
Qwen3 Coder Next vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 33.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in coding, where Step 3.5 Flash leads 41.7 to 35.8.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.12 / $0.80 for Qwen3 Coder Next.
- Qwen3 Coder Next accepts more context: 262K tokens versus 256K.
Side by side
| Qwen3 Coder Next | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 33.8 | 41.7 |
| Released | 2026-02-02 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 262K | 256K |
| Max output | 66K | 256K |
| Input $ / M tokens | $0.12 | $0.10 |
| Output $ / M tokens | $0.80 | $0.30 |
| Results tracked | 3 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Qwen3 Coder Next: 35.8 (#206), Step 3.5 Flash: 41.7 (#106)
| Benchmark | Qwen3 Coder Next | Step 3.5 Flash |
|---|---|---|
| SciCode | 32.3% | — |
| WeirdML | 34.4% | — |
| LMArena Coding | — | 1436 |
Reasoning Too close to call
Qwen3 Coder Next: 21.7 (#191), Step 3.5 Flash: 21.2 (#202)
| Benchmark | Qwen3 Coder Next | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1411 |
Math Not comparable
Qwen3 Coder Next: —, Step 3.5 Flash: 40.6 (#77)
| Benchmark | Qwen3 Coder Next | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| LMArena Math | — | 1408 |
Knowledge Not comparable
Qwen3 Coder Next: —, Step 3.5 Flash: 39.0 (#127)
| Benchmark | Qwen3 Coder Next | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1422 |
Multilingual Not comparable
Qwen3 Coder Next: —, Step 3.5 Flash: 50.7 (#115)
| Benchmark | Qwen3 Coder Next | 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 Coder Next: —, Step 3.5 Flash: 73.3 (#119)
| Benchmark | Qwen3 Coder Next | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |
Long Context Not comparable
Qwen3 Coder Next: —, Step 3.5 Flash: 42.8 (#112)
| Benchmark | Qwen3 Coder Next | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |
Writing & Preference Not comparable
Qwen3 Coder Next: —, Step 3.5 Flash: 59.0 (#108)
| Benchmark | Qwen3 Coder Next | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Qwen3 Coder Next better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 33.8 on the Noometry Index.
Which is cheaper, Qwen3 Coder Next 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 Coder Next lists at $0.12 and $0.80.
Is Qwen3 Coder Next or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Coder Next does, with 262K tokens against 256K.
How many benchmarks do Qwen3 Coder Next and Step 3.5 Flash share?
0 benchmarks have published results for both models. Qwen3 Coder Next has 3 scored results on Noometry and Step 3.5 Flash has 19.