Model comparison
Step 5 Preview vs Wizardlm 13b
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
StepFun
MicrosoftSummary
- They share 10 benchmarks with published results for both. Step 5 Preview scores higher in 7 categories and Wizardlm 13b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 30.5.
- Wizardlm 13b has downloadable open weights; the other is API-only.
Side by side
| Step 5 Preview | Wizardlm 13b | |
|---|---|---|
| Provider | StepFun | Microsoft |
| Noometry Index | 47.9 | 31.4 |
| Released | 2026-09-16 | — |
| Weights | Proprietary | Open |
| Context window | 1.02M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $2.70 | — |
| Results tracked | 18 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Step 5 Preview: 51.8 (#36), Wizardlm 13b: 30.1 (#298)
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 1480 | 1035 |
| LMArena WebDev | 1564 | — |
| SciCode | 58.9% | — |
Reasoning Step 5 Preview leads
Step 5 Preview: 40.0 (#57), Wizardlm 13b: 19.4 (#259)
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 1465 | 1018 |
| CritPt | 20.9% | — |
Math Step 5 Preview leads
Step 5 Preview: 46.1 (#72), Wizardlm 13b: 30.2 (#238)
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Math | 1470 | 1017 |
| ProofBench | 42% | — |
Knowledge Not comparable
Step 5 Preview: 41.2 (#112), Wizardlm 13b: —
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Expert | 1470 | — |
Multimodal Not comparable
Step 5 Preview: 41.0 (#41), Wizardlm 13b: —
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Vision | 1267 | — |
Multilingual Step 5 Preview leads
Step 5 Preview: 53.8 (#54), Wizardlm 13b: 27.1 (#277)
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 1432 | 1034 |
| LMArena Chinese | 1519 | 1023 |
| LMArena Russian | 1436 | — |
| LMArena Spanish | 1439 | — |
Instruction Following Step 5 Preview leads
Step 5 Preview: 76.0 (#50), Wizardlm 13b: 53.5 (#285)
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 1444 | 1048 |
Long Context Step 5 Preview leads
Step 5 Preview: 44.5 (#64), Wizardlm 13b: 32.0 (#273)
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | 1455 | 1054 |
Writing & Preference Step 5 Preview leads
Step 5 Preview: 62.8 (#71), Wizardlm 13b: 30.5 (#287)
| Benchmark | Step 5 Preview | Wizardlm 13b |
|---|---|---|
| LMArena Text | 1442 | 1077 |
| LMArena Creative Writing | 1410 | 1091 |
| LMArena Multi-Turn | 1447 | 1047 |
Frequently asked questions
Is Step 5 Preview better than Wizardlm 13b?
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.4 on the Noometry Index.
Is Step 5 Preview or Wizardlm 13b better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 30.1 in the Noometry coding category.
How many benchmarks do Step 5 Preview and Wizardlm 13b share?
10 benchmarks have published results for both models. Step 5 Preview has 18 scored results on Noometry and Wizardlm 13b has 10.