Model comparison
Qwen3-Coder 480B-A35B Instruct vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 17 benchmarks with published results for both. Qwen3-Coder 480B-A35B Instruct scores higher in 1 category and Step 3.5 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 3.5 Flash leads 42.4 to 35.5.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 256K.
Side by side
| Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 38.1 | 42.3 |
| Released | 2025-04 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 262K | 256K |
| Max output | 66K | 256K |
| Input $ / M tokens | $1.50 | $0.10 |
| Output $ / M tokens | $7.50 | $0.30 |
| Results tracked | 25 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Qwen3-Coder 480B-A35B Instruct: 35.5 (#223), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1412 | 1436 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1275 | — |
| GSO | 4.9% | — |
| WeirdML | 41.2% | — |
| ALE-Bench | 461.45 | — |
| AlgoTune | 1.44 | — |
Agentic & Tool Use Not comparable
Qwen3-Coder 480B-A35B Instruct: 23.9 (#123), Step 3.5 Flash: —
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 27.2% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Qwen3-Coder 480B-A35B Instruct: 25.5 (#149), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1411 |
| Kagi LLM Benchmark | 49.5% | — |
| NYT Connections (extended) | — | 28.4% |
Math Step 3.5 Flash leads
Qwen3-Coder 480B-A35B Instruct: 37.6 (#150), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1365 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
Knowledge Step 3.5 Flash leads
Qwen3-Coder 480B-A35B Instruct: 37.0 (#162), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1338 | 1421 |
Multilingual Step 3.5 Flash leads
Qwen3-Coder 480B-A35B Instruct: 47.7 (#148), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1346 | 1385 |
| LMArena Chinese | 1357 | 1447 |
| LMArena French | 1398 | 1421 |
| LMArena German | 1325 | 1405 |
| LMArena Japanese | 1310 | 1354 |
| LMArena Korean | 1305 | 1352 |
| LMArena Russian | 1366 | 1385 |
| LMArena Spanish | 1360 | 1419 |
Instruction Following Step 3.5 Flash leads
Qwen3-Coder 480B-A35B Instruct: 71.6 (#147), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1355 | 1385 |
Long Context Too close to call
Qwen3-Coder 480B-A35B Instruct: 42.0 (#131), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1378 | 1402 |
Writing & Preference Step 3.5 Flash leads
Qwen3-Coder 480B-A35B Instruct: 55.3 (#147), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1357 | 1403 |
| LMArena Creative Writing | 1333 | 1357 |
| LMArena Multi-Turn | 1365 | 1405 |
Frequently asked questions
Is Qwen3-Coder 480B-A35B Instruct better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index.
Which is cheaper, Qwen3-Coder 480B-A35B Instruct 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 480B-A35B Instruct lists at $1.50 and $7.50.
Is Qwen3-Coder 480B-A35B Instruct or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 256K.
How many benchmarks do Qwen3-Coder 480B-A35B Instruct and Step 3.5 Flash share?
17 benchmarks have published results for both models. Qwen3-Coder 480B-A35B Instruct has 25 scored results on Noometry and Step 3.5 Flash has 19.