Model comparison
Llama 3.2 90B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
Meta
StepFunSummary
- They share 1 benchmark with published results for both. Llama 3.2 90B scores higher in 0 categories and Step 5 Preview in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | Step 5 Preview | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 27.5 | 47.9 |
| Released | 2024-09-24 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 9 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Step 5 Preview: 51.8 (#36)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 30.0 (#80), Step 5 Preview: —
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| BALROG | 27.3% | — |
Reasoning Step 5 Preview leads
Llama 3.2 90B: 21.7 (#217), Step 5 Preview: 40.0 (#57)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1465 |
| Epoch Capabilities Index | 125.5 | — |
Math Step 5 Preview leads
Llama 3.2 90B: 11.1 (#308), Step 5 Preview: 46.1 (#72)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
| MATH Level 5 | 39.4% | — |
Knowledge Step 5 Preview leads
Llama 3.2 90B: 21.7 (#274), Step 5 Preview: 41.2 (#112)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1470 |
| MMLU | 80.3% | — |
Multimodal Step 5 Preview leads
Llama 3.2 90B: 25.4 (#124), Step 5 Preview: 41.0 (#41)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1000 | 1267 |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
Llama 3.2 90B: —, Step 5 Preview: 76.0 (#50)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
Llama 3.2 90B: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Step 5 Preview: 62.8 (#71)
| Benchmark | Llama 3.2 90B | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Llama 3.2 90B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Step 5 Preview share?
1 benchmark has published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Step 5 Preview has 18.