Model comparison
Llama 2-7B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 29.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
Meta
StepFunSummary
- They share 13 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 28.0.
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-7B | Step 5 Preview | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 29.1 | 47.9 |
| Released | 2023-07-18 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 29 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Llama 2-7B: 29.2 (#307), Step 5 Preview: 51.8 (#36)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1002 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Llama 2-7B: 15.7 (#312), Step 5 Preview: 40.0 (#57)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1465 |
| CritPt | — | 20.9% |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 99.06 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Step 5 Preview leads
Llama 2-7B: 30.7 (#233), Step 5 Preview: 46.1 (#72)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1042 | 1470 |
| ProofBench | — | 42% |
| GSM8K | 16.7% | — |
Knowledge Step 5 Preview leads
Llama 2-7B: 28.2 (#248), Step 5 Preview: 41.2 (#112)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1036 | 1470 |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
| ScienceQA | 43.1% | — |
Multilingual Step 5 Preview leads
Llama 2-7B: 23.8 (#293), Step 5 Preview: 53.8 (#54)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 973 | 1432 |
| LMArena Chinese | 973 | 1519 |
| LMArena Russian | 995 | 1436 |
| LMArena Spanish | 1007 | 1439 |
| LMArena French | 970 | — |
| LMArena German | 978 | — |
Instruction Following Step 5 Preview leads
Llama 2-7B: 50.8 (#298), Step 5 Preview: 76.0 (#50)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1006 | 1444 |
Long Context Step 5 Preview leads
Llama 2-7B: 30.4 (#287), Step 5 Preview: 44.5 (#64)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 999 | 1455 |
Writing & Preference Step 5 Preview leads
Llama 2-7B: 28.0 (#298), Step 5 Preview: 62.8 (#71)
| Benchmark | Llama 2-7B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1053 | 1442 |
| LMArena Creative Writing | 1033 | 1410 |
| LMArena Multi-Turn | 1029 | 1447 |
Frequently asked questions
Is Llama 2-7B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 29.1 on the Noometry Index.
Is Llama 2-7B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Step 5 Preview share?
13 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Step 5 Preview has 18.