# Llama 3.2 1B vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 20.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-1b-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 21.3.

## Snapshot

| | Llama 3.2 1B | Step 3 |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 20.1 | 40.5 |
| Rank | 354 | 149 |
| Context | 60K | — |
| Input $/M | $0.027 | — |
| Output $/M | $0.20 | — |
| Weights | Open | Open |

## Coding

- Llama 3.2 1B: 21.1 (#338)
- Step 3: 40.1 (#147)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Coding | 1070 | 1367 |
| BigCodeBench Instruct | 8.2% | — |
| BigCodeBench Complete | 11.3% | — |

## Agentic & Tool Use

- Llama 3.2 1B: 14.6 (#150)
- Step 3: —

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |

## Reasoning

- Llama 3.2 1B: 16.2 (#308)
- Step 3: 28.4 (#105)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 101.99 | — |

## Math

- Llama 3.2 1B: 10.4 (#313)
- Step 3: 37.6 (#148)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Math | 1086 | 1366 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |

## Knowledge

- Llama 3.2 1B: 7.2 (#312)
- Step 3: 36.8 (#164)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Expert | 1007 | 1333 |
| GPQA Diamond | 23.9% | — |

## Multimodal

- Llama 3.2 1B: —
- Step 3: 35.5 (#86)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Llama 3.2 1B: 23.8 (#292)
- Step 3: 46.3 (#159)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Non-English | 973 | 1327 |
| LMArena Chinese | 959 | 1397 |
| LMArena German | 1014 | 1371 |
| LMArena Russian | 941 | 1331 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- Llama 3.2 1B: 52.4 (#290)
- Step 3: 70.4 (#164)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1031 | 1332 |

## Long Context

- Llama 3.2 1B: 31.9 (#274)
- Step 3: 40.3 (#157)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1050 | 1326 |

## Writing & Preference

- Llama 3.2 1B: 21.3 (#310)
- Step 3: 54.3 (#151)

| Benchmark | Llama 3.2 1B | Step 3 |
|---|---|---|
| LMArena Text | 1055 | 1350 |
| LMArena Creative Writing | 1033 | 1321 |
| LMArena Multi-Turn | 1030 | 1341 |
| EQ-Bench Creative Writing | 200 | — |

## FAQ

### Is Llama 3.2 1B better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 20.1 on the Noometry Index.

### Is Llama 3.2 1B or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 21.1 in the Noometry coding category.

### How many benchmarks do Llama 3.2 1B and Step 3 share?

13 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Step 3 has 17.