# Codellama 34b Instruct vs Grok-3 mini

> Grok-3 mini is the stronger model overall, scoring 41.0 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-34b-instruct-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Grok-3 mini in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.7 to 52.4.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| Provider | Meta | xAI |
| Noometry Index | 30.2 | 41.0 |
| Rank | 285 | 130 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Codellama 34b Instruct: 28.0 (#310)
- Grok-3 mini: 40.4 (#126)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1046 | 1380 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |

## Reasoning

- Codellama 34b Instruct: 18.8 (#250)
- Grok-3 mini: 13.8 (#323)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1374 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |

## Math

- Codellama 34b Instruct: 28.5 (#227)
- Grok-3 mini: 40.3 (#78)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Math | 1056 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |

## Knowledge

- Codellama 34b Instruct: —
- Grok-3 mini: 46.3 (#75)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
| LMArena Expert | — | 1395 |

## Multilingual

- Codellama 34b Instruct: 25.9 (#279)
- Grok-3 mini: 48.3 (#141)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1011 | 1352 |
| LMArena Chinese | 976 | 1387 |
| LMArena French | — | 1357 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1343 |
| LMArena Korean | — | 1336 |
| LMArena Russian | — | 1352 |
| LMArena Spanish | — | 1379 |

## Instruction Following

- Codellama 34b Instruct: 52.4 (#286)
- Grok-3 mini: 78.7 (#8)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1028 | 1356 |
| IFEval | — | 95.1% |

## Long Context

- Codellama 34b Instruct: 30.8 (#279)
- Grok-3 mini: 41.0 (#142)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1014 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Codellama 34b Instruct: 28.4 (#292)
- Grok-3 mini: 52.7 (#163)

| Benchmark | Codellama 34b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Text | 1066 | 1370 |
| LMArena Creative Writing | 1032 | 1342 |
| LMArena Multi-Turn | 1015 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |

## FAQ

### Is Codellama 34b Instruct better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.0 to 30.2 on the Noometry Index.

### Is Codellama 34b Instruct or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 28.0 in the Noometry coding category.

### How many benchmarks do Codellama 34b Instruct and Grok-3 mini share?

10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Grok-3 mini has 35.