# Codellama 70b Instruct vs Gemma 1.1 2b IT

> Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gemma-1-1-2b-it
- Last updated: 2026-10-11
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Codellama 70b Instruct scores higher in 5 categories and Gemma 1.1 2b IT in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Codellama 70b Instruct leads 33.4 to 25.1.

## Snapshot

| | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| Provider | Meta | Google |
| Noometry Index | 33.7 | 29.3 |
| Rank | 237 | 313 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Gemma 1.1 2b IT: 30.1 (#299)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| HumanEval+ | 65.9% | 17.7% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1034 |
| BigCodeBench Complete | 49.6% | — |
| MBPP+ | — | 23.3% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Gemma 1.1 2b IT: 19.1 (#270)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1005 |

## Math

- Codellama 70b Instruct: —
- Gemma 1.1 2b IT: 30.8 (#232)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Math | — | 1047 |

## Knowledge

- Codellama 70b Instruct: —
- Gemma 1.1 2b IT: 26.5 (#258)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Expert | — | 970 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Gemma 1.1 2b IT: 24.6 (#289)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Non-English | 992 | 988 |
| LMArena Chinese | — | 1012 |
| LMArena German | — | 944 |
| LMArena Korean | — | 899 |
| LMArena Russian | — | 990 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Gemma 1.1 2b IT: 49.9 (#299)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Instruction Following | 1024 | 992 |

## Long Context

- Codellama 70b Instruct: —
- Gemma 1.1 2b IT: 30.6 (#286)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Longer Query | — | 1003 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Gemma 1.1 2b IT: 25.1 (#306)

| Benchmark | Codellama 70b Instruct | Gemma 1.1 2b IT |
|---|---|---|
| LMArena Text | 1057 | 1022 |
| LMArena Creative Writing | — | 998 |
| LMArena Multi-Turn | — | 959 |

## FAQ

### Is Codellama 70b Instruct better than Gemma 1.1 2b IT?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.3 on the Noometry Index.

### Is Codellama 70b Instruct or Gemma 1.1 2b IT better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 30.1 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Gemma 1.1 2b IT share?

5 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemma 1.1 2b IT has 16.