# Codestral vs Granite 3.0 8b Instruct

> Codestral and Granite 3.0 8b Instruct score almost the same on the Noometry Index (30.1 vs 31.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/codestral-vs-granite-3-0-8b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Codestral scores higher in 0 categories and Granite 3.0 8b Instruct in 2 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 35.4% for Granite 3.0 8b Instruct.

## Snapshot

| | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.1 | 31.1 |
| Rank | 287 | 266 |
| Context | 256K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- Granite 3.0 8b Instruct: 29.1 (#297)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 29.3% |
| BigCodeBench Complete | 52.5% | 35.4% |
| Aider Polyglot | 11.1% | — |
| LMArena Coding | — | 1113 |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.1 (#244)
- Granite 3.0 8b Instruct: 20.0 (#227)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1092 |

## Math

- Codestral: —
- Granite 3.0 8b Instruct: 30.3 (#211)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Math | — | 1143 |

## Knowledge

- Codestral: —
- Granite 3.0 8b Instruct: 29.1 (#233)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Expert | — | 1087 |

## Multilingual

- Codestral: —
- Granite 3.0 8b Instruct: 27.4 (#271)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Non-English | — | 1037 |
| LMArena Chinese | — | 1063 |
| LMArena Russian | — | 1060 |

## Instruction Following

- Codestral: —
- Granite 3.0 8b Instruct: 56.2 (#271)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1088 |

## Long Context

- Codestral: —
- Granite 3.0 8b Instruct: 34.0 (#247)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1122 |

## Writing & Preference

- Codestral: —
- Granite 3.0 8b Instruct: 31.2 (#280)

| Benchmark | Codestral | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Text | — | 1096 |
| LMArena Creative Writing | — | 1071 |
| LMArena Multi-Turn | — | 1063 |

## FAQ

### Is Codestral better than Granite 3.0 8b Instruct?

Codestral and Granite 3.0 8b Instruct score almost the same on the Noometry Index (30.1 vs 31.1), so choose on price, context window or the category you care about most.

### Is Codestral or Granite 3.0 8b Instruct better for coding?

Granite 3.0 8b Instruct scores higher on coding benchmarks: 29.1 versus 26.9 in the Noometry coding category.

### How many benchmarks do Codestral and Granite 3.0 8b Instruct share?

2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Granite 3.0 8b Instruct has 14.