Model comparison
Step 3.5 Flash vs Wizardlm 70b
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFun
MicrosoftSummary
- They share 12 benchmarks with published results for both. Step 3.5 Flash scores higher in 7 categories and Wizardlm 70b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 34.8.
Side by side
| Step 3.5 Flash | Wizardlm 70b | |
|---|---|---|
| Provider | StepFun | Microsoft |
| Noometry Index | 42.3 | 33.0 |
| 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 | 19 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Step 3.5 Flash: 42.4 (#105), Wizardlm 70b: 31.4 (#285)
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1436 | 1081 |
Reasoning Step 3.5 Flash leads
Step 3.5 Flash: 22.2 (#202), Wizardlm 70b: 20.7 (#234)
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1079 |
| NYT Connections (extended) | 28.4% | — |
Math Step 3.5 Flash leads
Step 3.5 Flash: 42.6 (#84), Wizardlm 70b: 32.2 (#218)
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1408 | 1116 |
| MathArena Final-Answer Competitions | 66.8% | — |
Knowledge Not comparable
Step 3.5 Flash: 39.6 (#132), Wizardlm 70b: —
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1421 | — |
Multilingual Step 3.5 Flash leads
Step 3.5 Flash: 50.5 (#119), Wizardlm 70b: 29.6 (#265)
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1385 | 1078 |
| LMArena Chinese | 1447 | 1052 |
| LMArena German | 1405 | 1083 |
| LMArena Russian | 1385 | 1155 |
| LMArena French | 1421 | — |
| LMArena Japanese | 1354 | — |
| LMArena Korean | 1352 | — |
| LMArena Spanish | 1419 | — |
Instruction Following Step 3.5 Flash leads
Step 3.5 Flash: 73.1 (#124), Wizardlm 70b: 56.3 (#273)
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1385 | 1093 |
Long Context Step 3.5 Flash leads
Step 3.5 Flash: 42.8 (#117), Wizardlm 70b: 33.3 (#263)
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1402 | 1097 |
Writing & Preference Step 3.5 Flash leads
Step 3.5 Flash: 58.8 (#113), Wizardlm 70b: 34.8 (#269)
| Benchmark | Step 3.5 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1403 | 1120 |
| LMArena Creative Writing | 1357 | 1149 |
| LMArena Multi-Turn | 1405 | 1108 |
Frequently asked questions
Is Step 3.5 Flash better than Wizardlm 70b?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 33.0 on the Noometry Index.
Is Step 3.5 Flash or Wizardlm 70b better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 31.4 in the Noometry coding category.
How many benchmarks do Step 3.5 Flash and Wizardlm 70b share?
12 benchmarks have published results for both models. Step 3.5 Flash has 19 scored results on Noometry and Wizardlm 70b has 12.