Model comparison
Step 3 vs Wizardlm 70b
Step 3 is the stronger model overall, scoring 40.5 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 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 leads 54.3 to 34.8.
Side by side
| Step 3 | Wizardlm 70b | |
|---|---|---|
| Provider | StepFun | Microsoft |
| Noometry Index | 40.5 | 33.0 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Step 3: 40.1 (#147), Wizardlm 70b: 31.4 (#285)
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1367 | 1081 |
Reasoning Step 3 leads
Step 3: 28.4 (#105), Wizardlm 70b: 20.7 (#234)
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1355 | 1079 |
| Kagi LLM Benchmark | 62.3% | — |
Math Step 3 leads
Step 3: 37.6 (#148), Wizardlm 70b: 32.2 (#218)
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1366 | 1116 |
Knowledge Not comparable
Step 3: 36.8 (#164), Wizardlm 70b: —
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1333 | — |
Multimodal Not comparable
Step 3: 35.5 (#86), Wizardlm 70b: —
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Vision | 1177 | — |
Multilingual Step 3 leads
Step 3: 46.3 (#159), Wizardlm 70b: 29.6 (#265)
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1327 | 1078 |
| LMArena Chinese | 1397 | 1052 |
| LMArena German | 1371 | 1083 |
| LMArena Russian | 1331 | 1155 |
| LMArena Korean | 1269 | — |
| LMArena Spanish | 1371 | — |
Instruction Following Step 3 leads
Step 3: 70.4 (#164), Wizardlm 70b: 56.3 (#273)
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1332 | 1093 |
Long Context Step 3 leads
Step 3: 40.3 (#157), Wizardlm 70b: 33.3 (#263)
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1326 | 1097 |
Writing & Preference Step 3 leads
Step 3: 54.3 (#151), Wizardlm 70b: 34.8 (#269)
| Benchmark | Step 3 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1350 | 1120 |
| LMArena Creative Writing | 1321 | 1149 |
| LMArena Multi-Turn | 1341 | 1108 |
Frequently asked questions
Is Step 3 better than Wizardlm 70b?
Step 3 is the stronger model overall, scoring 40.5 to 33.0 on the Noometry Index.
Is Step 3 or Wizardlm 70b better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 31.4 in the Noometry coding category.
How many benchmarks do Step 3 and Wizardlm 70b share?
12 benchmarks have published results for both models. Step 3 has 17 scored results on Noometry and Wizardlm 70b has 12.