# Codestral vs Granite 3.1 8b Instruct

> Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 30.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-granite-3-1-8b-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Granite 3.1 8b Instruct leads 34.5 to 27.3.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| Provider | Mistral AI | IBM |
| Noometry Index | 30.6 | 32.4 |
| Rank | 290 | 258 |
| Context | 256K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Proprietary | Open |

## Coding

- Codestral: 27.3 (#321)
- Granite 3.1 8b Instruct: 34.5 (#233)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1186 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- Granite 3.1 8b Instruct: 24.1 (#120)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |

## Reasoning

- Codestral: 19.8 (#251)
- Granite 3.1 8b Instruct: 22.1 (#207)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1145 |

## Math

- Codestral: —
- Granite 3.1 8b Instruct: 33.0 (#209)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | — | 1152 |

## Knowledge

- Codestral: —
- Granite 3.1 8b Instruct: 31.1 (#220)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | — | 1142 |

## Multilingual

- Codestral: —
- Granite 3.1 8b Instruct: 30.9 (#260)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | — | 1099 |
| LMArena Chinese | — | 1145 |
| LMArena Russian | — | 1092 |

## Instruction Following

- Codestral: —
- Granite 3.1 8b Instruct: 58.6 (#259)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1131 |

## Long Context

- Codestral: —
- Granite 3.1 8b Instruct: 35.2 (#241)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1162 |

## Writing & Preference

- Codestral: —
- Granite 3.1 8b Instruct: 35.5 (#266)

| Benchmark | Codestral | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | — | 1150 |
| LMArena Creative Writing | — | 1129 |
| LMArena Multi-Turn | — | 1108 |

## FAQ

### Is Codestral better than Granite 3.1 8b Instruct?

Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 30.6 on the Noometry Index.

### Is Codestral or Granite 3.1 8b Instruct better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 27.3 in the Noometry coding category.

### How many benchmarks do Codestral and Granite 3.1 8b Instruct share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Granite 3.1 8b Instruct has 13.