# Codestral vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 30.1 on the Noometry Index. Codestral costs 4.4× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-muse-spark-1-2
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 19.1.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 256K.
- Codestral has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | Muse Spark 1.2 |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 30.1 | 49.8 |
| Rank | 287 | 44 |
| Context | 256K | 1.05M |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $0.90 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- Codestral: 26.9 (#316)
- Muse Spark 1.2: 48.6 (#49)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| DeepSWE | — | 54.9% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1532 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1497 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- Muse Spark 1.2: 29.5 (#77)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |

## Reasoning

- Codestral: 19.1 (#244)
- Muse Spark 1.2: 50.4 (#32)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| LMArena Hard Prompts | — | 1490 |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 155.18 |

## Math

- Codestral: —
- Muse Spark 1.2: 43.8 (#68)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |

## Knowledge

- Codestral: —
- Muse Spark 1.2: 53.9 (#49)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | — | 60.3% |
| LMArena Expert | — | 1485 |

## Multimodal

- Codestral: —
- Muse Spark 1.2: 42.6 (#24)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |

## Multilingual

- Codestral: —
- Muse Spark 1.2: 57.4 (#10)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | — | 1479 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1494 |

## Instruction Following

- Codestral: —
- Muse Spark 1.2: 77.1 (#30)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | — | 1466 |

## Long Context

- Codestral: —
- Muse Spark 1.2: 45.4 (#35)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | — | 1483 |

## Writing & Preference

- Codestral: —
- Muse Spark 1.2: 72.6 (#14)

| Benchmark | Codestral | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | — | 1486 |
| LMArena Creative Writing | — | 1444 |
| EQ-Bench Creative Writing | — | 1840 |
| LMArena Multi-Turn | — | 1504 |

## FAQ

### Is Codestral better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 30.1 on the Noometry Index. Codestral costs 4.4× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

### Which is cheaper, Codestral or Muse Spark 1.2?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

### Is Codestral or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 256K.

### How many benchmarks do Codestral and Muse Spark 1.2 share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Muse Spark 1.2 has 28.