# Llama 2-13B vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-13b-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 2-13B 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 30.0.

## Snapshot

| | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 29.1 | 41.7 |
| Rank | 304 | 116 |
| Context | — | 256K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Llama 2-13B: 30.4 (#287)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1062 | 1436 |

## Reasoning

- Llama 2-13B: 12.3 (#333)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 105.8 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |

## Math

- Llama 2-13B: 28.7 (#226)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1065 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| GSM8K | 36.9% | — |

## Knowledge

- Llama 2-13B: 27.5 (#244)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1030 | 1422 |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |

## Multimodal

- Llama 2-13B: —
- Step 3.5 Flash: —

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| ScienceQA | 55.8% | — |

## Multilingual

- Llama 2-13B: 26.7 (#274)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1024 | 1386 |
| LMArena Chinese | 1001 | 1448 |
| LMArena French | 1043 | 1421 |
| LMArena German | 1009 | 1404 |
| LMArena Japanese | 894 | 1353 |
| LMArena Korean | 953 | 1350 |
| LMArena Russian | 1055 | 1385 |
| LMArena Spanish | 1086 | 1419 |

## Instruction Following

- Llama 2-13B: 53.5 (#282)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1046 | 1385 |

## Long Context

- Llama 2-13B: 32.3 (#264)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1064 | 1402 |

## Writing & Preference

- Llama 2-13B: 30.0 (#284)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Llama 2-13B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1085 | 1403 |
| LMArena Creative Writing | 1047 | 1357 |
| LMArena Multi-Turn | 1050 | 1405 |

## FAQ

### Is Llama 2-13B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 29.1 on the Noometry Index.

### Is Llama 2-13B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 30.4 in the Noometry coding category.

### How many benchmarks do Llama 2-13B and Step 3.5 Flash share?

17 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Step 3.5 Flash has 19.