# Codestral vs Llama 3-8B

> Codestral is the stronger model overall, scoring 30.1 to 25.3 on the Noometry Index. Llama 3-8B costs 3.2× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-llama-3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codestral scores higher in 1 category and Llama 3-8B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codestral leads 19.1 to 13.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Codestral and 36.9% for Llama 3-8B.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 8K.

## Snapshot

| | Codestral | Llama 3-8B |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 30.1 | 25.3 |
| Rank | 287 | 338 |
| Context | 256K | 8K |
| Input $/M | $0.30 | $0.14 |
| Output $/M | $0.90 | $0.14 |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- Llama 3-8B: 30.5 (#285)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 31.9% |
| BigCodeBench Complete | 52.5% | 36.9% |
| HumanEval+ | 73.8% | 56.7% |
| MBPP+ | 61.9% | 54.8% |
| Aider Polyglot | 11.1% | — |
| LMArena Coding | — | 1152 |
| ALE-Bench | 137.78 | — |

## Reasoning

- Codestral: 19.1 (#244)
- Llama 3-8B: 13.8 (#321)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1133 |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| Epoch Capabilities Index | — | 116.33 |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |

## Math

- Codestral: —
- Llama 3-8B: 8.3 (#317)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| LMArena Math | — | 1151 |
| MATH Level 5 | — | 6.1% |

## Knowledge

- Codestral: —
- Llama 3-8B: 7.8 (#303)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| GPQA Diamond | — | 26.1% |
| LMArena Expert | — | 1113 |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |

## Multilingual

- Codestral: —
- Llama 3-8B: 31.0 (#256)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Non-English | — | 1098 |
| LMArena Chinese | — | 1076 |
| LMArena French | — | 1158 |
| LMArena German | — | 1104 |
| LMArena Japanese | — | 967 |
| LMArena Korean | — | 1003 |
| LMArena Russian | — | 1109 |
| LMArena Spanish | — | 1172 |

## Instruction Following

- Codestral: —
- Llama 3-8B: 58.7 (#255)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | — | 1127 |

## Long Context

- Codestral: —
- Llama 3-8B: 34.2 (#246)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | — | 1128 |

## Writing & Preference

- Codestral: —
- Llama 3-8B: 37.7 (#251)

| Benchmark | Codestral | Llama 3-8B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1150 |
| LMArena Multi-Turn | — | 1152 |

## FAQ

### Is Codestral better than Llama 3-8B?

Codestral is the stronger model overall, scoring 30.1 to 25.3 on the Noometry Index. Llama 3-8B costs 3.2× less per token, which makes it the better buy when Codestral's lead doesn't matter for your workload.

### Which is cheaper, Codestral or Llama 3-8B?

Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; Codestral lists at $0.30 and $0.90.

### Is Codestral or Llama 3-8B better for coding?

Llama 3-8B scores higher on coding benchmarks: 30.5 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

Codestral does, with 256K tokens against 8K.

### How many benchmarks do Codestral and Llama 3-8B share?

4 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Llama 3-8B has 34.