# Codellama 34b Instruct vs Gemma 4 26B A4B IT

> Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-gemma-4-26b-a4b-it
- Last updated: 2026-10-11
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and Gemma 4 26B A4B IT in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 26B A4B IT leads 58.6 to 28.2.

## Snapshot

| | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| Provider | Meta | Google |
| Noometry Index | 30.8 | 43.5 |
| Rank | 287 | 92 |
| Context | — | 262K |
| Input $/M | — | $0.0675 |
| Output $/M | — | $0.23 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.5 (#314)
- Gemma 4 26B A4B IT: 39.0 (#164)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Coding | 1046 | 1447 |
| LMArena WebDev | — | 1359 |
| SciCode | — | 40% |
| WeirdML | — | 35.2% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 927.17 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Reasoning

- Codellama 34b Instruct: 19.6 (#255)
- Gemma 4 26B A4B IT: 21.8 (#213)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1439 |
| CritPt | — | 0% |
| Chess Puzzles | — | 6% |
| DTBench | — | 74.9% |
| LMCA | — | 29.7% |
| Epoch Capabilities Index | — | 141.85 |

## Math

- Codellama 34b Instruct: 31.0 (#230)
- Gemma 4 26B A4B IT: 47.6 (#67)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Math | 1056 | 1470 |
| OTIS Mock AIME 2024-2025 | — | 82.2% |

## Knowledge

- Codellama 34b Instruct: —
- Gemma 4 26B A4B IT: 45.7 (#85)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | — | 73.2% |
| Vectara Hallucination Rate | — | 5.2% |
| LMArena Expert | — | 1447 |

## Multimodal

- Codellama 34b Instruct: —
- Gemma 4 26B A4B IT: 40.6 (#46)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | — | 1260 |

## Multilingual

- Codellama 34b Instruct: 25.8 (#284)
- Gemma 4 26B A4B IT: 53.1 (#71)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1011 | 1421 |
| LMArena Chinese | 976 | 1495 |
| LMArena French | — | 1460 |
| LMArena Russian | — | 1434 |
| LMArena Spanish | — | 1417 |

## Instruction Following

- Codellama 34b Instruct: 52.2 (#291)
- Gemma 4 26B A4B IT: 74.8 (#82)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1028 | 1420 |

## Long Context

- Codellama 34b Instruct: 30.9 (#284)
- Gemma 4 26B A4B IT: 43.6 (#91)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1013 | 1428 |

## Writing & Preference

- Codellama 34b Instruct: 28.2 (#297)
- Gemma 4 26B A4B IT: 58.6 (#115)

| Benchmark | Codellama 34b Instruct | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1066 | 1434 |
| LMArena Creative Writing | 1032 | 1402 |
| LMArena Multi-Turn | 1015 | 1441 |
| EQ-Bench Creative Writing | — | 1305 |

## FAQ

### Is Codellama 34b Instruct better than Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 30.8 on the Noometry Index.

### Is Codellama 34b Instruct or Gemma 4 26B A4B IT better for coding?

Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 28.5 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and Gemma 4 26B A4B IT share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Gemma 4 26B A4B IT has 28.