Model comparison
Step 3 vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 40.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. Step 3 scores higher in 1 category and Step 3.5 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 22.2.
Side by side
| Step 3 | Step 3.5 Flash | |
|---|---|---|
| Provider | StepFun | StepFun |
| Noometry Index | 40.5 | 42.3 |
| Released | — | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 17 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Step 3: 40.1 (#147), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1367 | 1436 |
Reasoning Step 3 leads
Step 3: 28.4 (#105), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1355 | 1411 |
| Kagi LLM Benchmark | 62.3% | — |
| NYT Connections (extended) | — | 28.4% |
Math Step 3.5 Flash leads
Step 3: 37.6 (#148), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1366 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
Knowledge Step 3.5 Flash leads
Step 3: 36.8 (#164), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1333 | 1421 |
Multimodal Not comparable
Step 3: 35.5 (#86), Step 3.5 Flash: —
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1177 | — |
Multilingual Step 3.5 Flash leads
Step 3: 46.3 (#159), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1327 | 1385 |
| LMArena Chinese | 1397 | 1447 |
| LMArena German | 1371 | 1405 |
| LMArena Korean | 1269 | 1352 |
| LMArena Russian | 1331 | 1385 |
| LMArena Spanish | 1371 | 1419 |
| LMArena French | — | 1421 |
| LMArena Japanese | — | 1354 |
Instruction Following Step 3.5 Flash leads
Step 3: 70.4 (#164), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1332 | 1385 |
Long Context Step 3.5 Flash leads
Step 3: 40.3 (#157), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1326 | 1402 |
Writing & Preference Step 3.5 Flash leads
Step 3: 54.3 (#151), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Step 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1350 | 1403 |
| LMArena Creative Writing | 1321 | 1357 |
| LMArena Multi-Turn | 1341 | 1405 |
Frequently asked questions
Is Step 3 better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 40.5 on the Noometry Index.
Is Step 3 or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 40.1 in the Noometry coding category.
How many benchmarks do Step 3 and Step 3.5 Flash share?
15 benchmarks have published results for both models. Step 3 has 17 scored results on Noometry and Step 3.5 Flash has 19.