Model comparison
Llama 13b vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Meta
StepFunSummary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Step 5 Preview in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 13.8.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| Llama 13b | Step 5 Preview | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 24.4 | 47.9 |
| Released | 2023-02-24 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 21 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Llama 13b: 21.4 (#337), Step 5 Preview: 51.8 (#36)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Coding | 683 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Llama 13b: 14.0 (#329), Step 5 Preview: 40.0 (#57)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 728 | 1465 |
| CritPt | — | 20.9% |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Step 5 Preview leads
Llama 13b: 26.7 (#256), Step 5 Preview: 46.1 (#72)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Math | 838 | 1470 |
| ProofBench | — | 42% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
| ScienceQA | 43.3% | — |
Multilingual Step 5 Preview leads
Llama 13b: 16.6 (#297), Step 5 Preview: 53.8 (#54)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 819 | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Llama 13b: 36.7 (#305), Step 5 Preview: 76.0 (#50)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 781 | 1444 |
Long Context Not comparable
Llama 13b: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Step 5 Preview leads
Llama 13b: 13.8 (#312), Step 5 Preview: 62.8 (#71)
| Benchmark | Llama 13b | Step 5 Preview |
|---|---|---|
| LMArena Text | 834 | 1442 |
| LMArena Creative Writing | 794 | 1410 |
| LMArena Multi-Turn | 753 | 1447 |
Frequently asked questions
Is Llama 13b better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 24.4 on the Noometry Index.
Is Llama 13b or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Step 5 Preview share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Step 5 Preview has 18.