# Codellama 70b Instruct vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 42.3 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-step-3-5-flash
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Step 3.5 Flash in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Step 3.5 Flash leads 50.5 to 24.8.

## Snapshot

| | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 33.7 | 42.3 |
| Rank | 237 | 116 |
| Context | — | 256K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1436 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1411 |
| NYT Connections (extended) | — | 28.4% |

## Math

- Codellama 70b Instruct: —
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| LMArena Math | — | 1408 |

## Knowledge

- Codellama 70b Instruct: —
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1421 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 992 | 1385 |
| LMArena Chinese | — | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1024 | 1385 |

## Long Context

- Codellama 70b Instruct: —
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | — | 1402 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Codellama 70b Instruct | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1057 | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |

## FAQ

### Is Codellama 70b Instruct better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Step 3.5 Flash share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Step 3.5 Flash has 19.