Model comparison
Llama 3-70B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 28.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Meta
StepFunSummary
- They share 13 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 12.8.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | Step 5 Preview | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 28.8 | 47.9 |
| Released | 2024-04-18 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 31 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Llama 3-70B: 35.8 (#218), Step 5 Preview: 51.8 (#36)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1206 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Step 5 Preview: —
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| Cybench | 5% | — |
Reasoning Step 5 Preview leads
Llama 3-70B: 18.0 (#288), Step 5 Preview: 40.0 (#57)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1465 |
| Kagi LLM Benchmark | 35.1% | — |
| CritPt | — | 20.9% |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Step 5 Preview leads
Llama 3-70B: 12.8 (#305), Step 5 Preview: 46.1 (#72)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1218 | 1470 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| ProofBench | — | 42% |
| MATH Level 5 | 22.6% | — |
Knowledge Step 5 Preview leads
Llama 3-70B: 20.8 (#277), Step 5 Preview: 41.2 (#112)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1149 | 1470 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |
Multimodal Not comparable
Llama 3-70B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Llama 3-70B: 33.6 (#251), Step 5 Preview: 53.8 (#54)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1142 | 1432 |
| LMArena Chinese | 1114 | 1519 |
| LMArena Russian | 1159 | 1436 |
| LMArena Spanish | 1241 | 1439 |
| LMArena French | 1232 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
Instruction Following Step 5 Preview leads
Llama 3-70B: 62.5 (#238), Step 5 Preview: 76.0 (#50)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1194 | 1444 |
Long Context Step 5 Preview leads
Llama 3-70B: 35.6 (#240), Step 5 Preview: 44.5 (#64)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1174 | 1455 |
Writing & Preference Step 5 Preview leads
Llama 3-70B: 42.8 (#231), Step 5 Preview: 62.8 (#71)
| Benchmark | Llama 3-70B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1221 | 1442 |
| LMArena Creative Writing | 1210 | 1410 |
| LMArena Multi-Turn | 1223 | 1447 |
Frequently asked questions
Is Llama 3-70B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 28.8 on the Noometry Index.
Is Llama 3-70B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Step 5 Preview share?
13 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Step 5 Preview has 18.