# Codestral vs Grok 3

> Grok 3 is the stronger model overall, scoring 39.6 to 30.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-grok-3
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Codestral scores higher in 1 category and Grok 3 in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Grok 3 leads 41.5 to 26.9.
- The biggest single-benchmark swing is Aider Polyglot: 11.1% for Codestral and 53.3% for Grok 3.
- Codestral has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | Grok 3 |
|---|---|---|
| Provider | Mistral AI | xAI |
| Noometry Index | 30.1 | 39.6 |
| Rank | 287 | 150 |
| Context | 256K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Open | Proprietary |

## Coding

- Codestral: 26.9 (#316)
- Grok 3: 41.5 (#113)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| Aider Polyglot | 11.1% | 53.3% |
| WeirdML | — | 37.2% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1432 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- Grok 3: 30.2 (#69)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| BALROG | — | 29.5% |

## Reasoning

- Codestral: 19.1 (#244)
- Grok 3: 13.8 (#322)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 61.3% |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 36.1% |
| ARC-AGI-1 | — | 5.5% |
| LMArena Hard Prompts | — | 1433 |
| Epoch Capabilities Index | — | 138.34 |

## Math

- Codestral: —
- Grok 3: 36.2 (#122)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| Omni-MATH | — | 46.4% |
| LMArena Math | — | 1390 |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Codestral: —
- Grok 3: 46.0 (#76)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 78.8% |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 5.8% |
| GPQA (HELM) | — | 65% |
| LMArena Expert | — | 1420 |

## Multilingual

- Codestral: —
- Grok 3: 52.5 (#81)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| LMArena Non-English | — | 1411 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1460 |
| LMArena German | — | 1431 |
| LMArena Japanese | — | 1389 |
| LMArena Korean | — | 1374 |
| LMArena Russian | — | 1416 |
| LMArena Spanish | — | 1417 |

## Instruction Following

- Codestral: —
- Grok 3: 75.2 (#69)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| IFEval | — | 88.4% |
| LMArena Instruction Following | — | 1409 |

## Long Context

- Codestral: —
- Grok 3: 38.7 (#187)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| Fiction.LiveBench | — | 58.3% |
| LMArena Longer Query | — | 1439 |

## Writing & Preference

- Codestral: —
- Grok 3: 56.0 (#136)

| Benchmark | Codestral | Grok 3 |
|---|---|---|
| LMArena Text | — | 1426 |
| LMArena Creative Writing | — | 1414 |
| Short-Story Creative Writing | — | 76.4% |
| EQ-Bench Creative Writing | — | 1186 |
| WildBench | — | 84.9% |
| LMArena Multi-Turn | — | 1424 |

## FAQ

### Is Codestral better than Grok 3?

Grok 3 is the stronger model overall, scoring 39.6 to 30.1 on the Noometry Index.

### Is Codestral or Grok 3 better for coding?

Grok 3 scores higher on coding benchmarks: 41.5 versus 26.9 in the Noometry coding category.

### How many benchmarks do Codestral and Grok 3 share?

2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Grok 3 has 40.