# Codellama 70b Instruct vs Gemini 1.0 Pro

> Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-gemini-1-0-pro
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Gemini 1.0 Pro in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemini 1.0 Pro leads 33.5 to 24.9.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| Provider | Meta | Google |
| Noometry Index | 33.3 | 27.1 |
| Rank | 236 | 327 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Gemini 1.0 Pro: 31.6 (#270)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| HumanEval+ | 65.9% | 55.5% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1108 |
| BigCodeBench Complete | 49.6% | — |
| MBPP+ | — | 61.4% |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Gemini 1.0 Pro: 16.4 (#292)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1109 |
| DTBench | — | 45.9% |
| Epoch Capabilities Index | — | 116.97 |

## Math

- Codellama 70b Instruct: —
- Gemini 1.0 Pro: 8.7 (#315)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| LMArena Math | — | 1132 |
| MATH Level 5 | — | 11.2% |

## Knowledge

- Codellama 70b Instruct: —
- Gemini 1.0 Pro: 15.5 (#286)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | — | 34% |
| LMArena Expert | — | 1059 |
| MMLU | — | 70% |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Gemini 1.0 Pro: 33.5 (#247)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 992 | 1138 |
| LMArena Chinese | — | 1124 |
| LMArena French | — | 1144 |
| LMArena German | — | 1125 |
| LMArena Japanese | — | 1023 |
| LMArena Russian | — | 1186 |
| LMArena Spanish | — | 1118 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Gemini 1.0 Pro: 57.9 (#262)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1024 | 1114 |

## Long Context

- Codellama 70b Instruct: —
- Gemini 1.0 Pro: 34.3 (#244)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | — | 1132 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Gemini 1.0 Pro: 36.2 (#259)

| Benchmark | Codellama 70b Instruct | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1057 | 1149 |
| LMArena Creative Writing | — | 1130 |
| LMArena Multi-Turn | — | 1139 |

## FAQ

### Is Codellama 70b Instruct better than Gemini 1.0 Pro?

Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 27.1 on the Noometry Index.

### Is Codellama 70b Instruct or Gemini 1.0 Pro better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 31.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Gemini 1.0 Pro share?

5 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Gemini 1.0 Pro has 24.