Model comparison
Step 3.7 Flash vs Wizardlm 70b
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 33.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFun
MicrosoftSummary
- The widest gap is in math, where Step 3.7 Flash leads 42.9 to 32.2.
Side by side
| Step 3.7 Flash | Wizardlm 70b | |
|---|---|---|
| Provider | StepFun | Microsoft |
| Noometry Index | 37.3 | 33.0 |
| Released | 2026-05-29 | — |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.18 | — |
| Output $ / M tokens | $1.11 | — |
| Results tracked | 5 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
Step 3.7 Flash: 40.0 (#150), Wizardlm 70b: 31.4 (#285)
| Benchmark | Step 3.7 Flash | Wizardlm 70b |
|---|---|---|
| SciCode | 40% | — |
| LMArena Coding | — | 1081 |
| ALE-Bench | 694.12 | — |
Reasoning Too close to call
Step 3.7 Flash: 21.6 (#219), Wizardlm 70b: 20.7 (#234)
| Benchmark | Step 3.7 Flash | Wizardlm 70b |
|---|---|---|
| NYT Connections (extended) | 39.7% | — |
| CritPt | 2.3% | — |
| LMArena Hard Prompts | — | 1079 |
Math Step 3.7 Flash leads
Step 3.7 Flash: 42.9 (#82), Wizardlm 70b: 32.2 (#218)
| Benchmark | Step 3.7 Flash | Wizardlm 70b |
|---|---|---|
| MathArena Final-Answer Competitions | 68.5% | — |
| LMArena Math | — | 1116 |
Multilingual Not comparable
Step 3.7 Flash: —, Wizardlm 70b: 29.6 (#265)
| Benchmark | Step 3.7 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | — | 1078 |
| LMArena Chinese | — | 1052 |
| LMArena German | — | 1083 |
| LMArena Russian | — | 1155 |
Instruction Following Not comparable
Step 3.7 Flash: —, Wizardlm 70b: 56.3 (#273)
| Benchmark | Step 3.7 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | — | 1093 |
Long Context Not comparable
Step 3.7 Flash: —, Wizardlm 70b: 33.3 (#263)
| Benchmark | Step 3.7 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | — | 1097 |
Writing & Preference Not comparable
Step 3.7 Flash: —, Wizardlm 70b: 34.8 (#269)
| Benchmark | Step 3.7 Flash | Wizardlm 70b |
|---|---|---|
| LMArena Text | — | 1120 |
| LMArena Creative Writing | — | 1149 |
| LMArena Multi-Turn | — | 1108 |
Frequently asked questions
Is Step 3.7 Flash better than Wizardlm 70b?
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 33.0 on the Noometry Index.
Is Step 3.7 Flash or Wizardlm 70b better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 31.4 in the Noometry coding category.
How many benchmarks do Step 3.7 Flash and Wizardlm 70b share?
0 benchmarks have published results for both models. Step 3.7 Flash has 5 scored results on Noometry and Wizardlm 70b has 12.