# Llama 3.2 3B vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 28.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-3b-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 59.0 to 24.9.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
- Step 3.5 Flash accepts more context: 256K tokens versus 131K.

## Snapshot

| | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 28.4 | 41.7 |
| Rank | 318 | 116 |
| Context | 131K | 256K |
| Input $/M | $0.05 | $0.10 |
| Output $/M | $0.33 | $0.30 |
| Weights | Open | Open |

## Coding

- Llama 3.2 3B: 27.1 (#314)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1098 | 1436 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |

## Agentic & Tool Use

- Llama 3.2 3B: 19.9 (#135)
- Step 3.5 Flash: —

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |

## Reasoning

- Llama 3.2 3B: 20.1 (#225)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1411 |
| NYT Connections (extended) | — | 28.4% |

## Math

- Llama 3.2 3B: 29.9 (#213)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1126 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- Llama 3.2 3B: 29.1 (#232)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1090 | 1422 |

## Multilingual

- Llama 3.2 3B: 26.4 (#276)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1019 | 1386 |
| LMArena Chinese | 1017 | 1448 |
| LMArena German | 1056 | 1404 |
| LMArena Russian | 949 | 1385 |
| LMArena French | — | 1421 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- Llama 3.2 3B: 56.3 (#270)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1089 | 1385 |

## Long Context

- Llama 3.2 3B: 33.4 (#256)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1101 | 1402 |

## Writing & Preference

- Llama 3.2 3B: 24.9 (#302)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Llama 3.2 3B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1110 | 1403 |
| LMArena Creative Writing | 1094 | 1357 |
| LMArena Multi-Turn | 1105 | 1405 |
| EQ-Bench Creative Writing | 595 | — |

## FAQ

### Is Llama 3.2 3B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 28.4 on the Noometry Index.

### Which is cheaper, Llama 3.2 3B or Step 3.5 Flash?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.

### Is Llama 3.2 3B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 27.1 in the Noometry coding category.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 131K.

### How many benchmarks do Llama 3.2 3B and Step 3.5 Flash share?

13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Step 3.5 Flash has 19.