# Codellama 34b Instruct vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.3 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-mistral-medium
- Last updated: 2026-10-11
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Mistral Medium in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 28.2.

## Snapshot

| | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.8 | 36.3 |
| Rank | 287 | 218 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Open |

## Coding

- Codellama 34b Instruct: 28.5 (#314)
- Mistral Medium: 34.2 (#243)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Coding | 1046 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Agentic & Tool Use

- Codellama 34b Instruct: —
- Mistral Medium: 28.3 (#90)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Codellama 34b Instruct: 19.6 (#255)
- Mistral Medium: 24.0 (#167)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |

## Math

- Codellama 34b Instruct: 31.0 (#230)
- Mistral Medium: 28.1 (#245)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Math | 1056 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Codellama 34b Instruct: —
- Mistral Medium: 25.0 (#265)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |

## Multimodal

- Codellama 34b Instruct: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Codellama 34b Instruct: 25.8 (#284)
- Mistral Medium: 52.1 (#91)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1011 | 1408 |
| LMArena Chinese | 976 | 1447 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1433 |

## Instruction Following

- Codellama 34b Instruct: 52.2 (#291)
- Mistral Medium: 73.7 (#116)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1028 | 1398 |

## Long Context

- Codellama 34b Instruct: 30.9 (#284)
- Mistral Medium: 42.9 (#114)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1013 | 1406 |

## Writing & Preference

- Codellama 34b Instruct: 28.2 (#297)
- Mistral Medium: 60.0 (#103)

| Benchmark | Codellama 34b Instruct | Mistral Medium |
|---|---|---|
| LMArena Text | 1066 | 1424 |
| LMArena Creative Writing | 1032 | 1391 |
| LMArena Multi-Turn | 1015 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

### Is Codellama 34b Instruct better than Mistral Medium?

Mistral Medium is the stronger model overall, scoring 36.3 to 30.8 on the Noometry Index.

### Is Codellama 34b Instruct or Mistral Medium better for coding?

Mistral Medium scores higher on coding benchmarks: 34.2 versus 28.5 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and Mistral Medium share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Mistral Medium has 36.