# Codestral vs Longcat Flash Chat

> Longcat Flash Chat is the stronger model overall, scoring 42.1 to 30.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-longcat-flash-chat
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Codestral scores higher in 1 category and Longcat Flash Chat in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Longcat Flash Chat leads 43.5 to 27.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 43.9% for Longcat Flash Chat.
- Longcat Flash Chat has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | Longcat Flash Chat |
|---|---|---|
| Provider | Mistral AI | Meituan |
| Noometry Index | 30.6 | 42.1 |
| Rank | 290 | 120 |
| Context | 256K | — |
| Input $/M | $0.30 | — |
| Output $/M | $0.90 | — |
| Weights | Proprietary | Open |

## Coding

- Codestral: 27.3 (#321)
- Longcat Flash Chat: 43.5 (#87)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1471 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.8 (#251)
- Longcat Flash Chat: 19.0 (#272)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 43.9% |
| NYT Connections (extended) | — | 17.7% |
| LMArena Hard Prompts | — | 1440 |

## Math

- Codestral: —
- Longcat Flash Chat: 39.4 (#107)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| LMArena Math | — | 1442 |

## Knowledge

- Codestral: —
- Longcat Flash Chat: 40.6 (#116)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| LMArena Expert | — | 1454 |

## Multilingual

- Codestral: —
- Longcat Flash Chat: 51.9 (#101)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| LMArena Non-English | — | 1404 |
| LMArena Chinese | — | 1465 |
| LMArena French | — | 1456 |
| LMArena German | — | 1408 |
| LMArena Japanese | — | 1373 |
| LMArena Korean | — | 1371 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1445 |

## Instruction Following

- Codestral: —
- Longcat Flash Chat: 74.4 (#96)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| LMArena Instruction Following | — | 1411 |

## Long Context

- Codestral: —
- Longcat Flash Chat: 43.5 (#93)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| LMArena Longer Query | — | 1425 |

## Writing & Preference

- Codestral: —
- Longcat Flash Chat: 61.0 (#91)

| Benchmark | Codestral | Longcat Flash Chat |
|---|---|---|
| LMArena Text | — | 1427 |
| LMArena Creative Writing | — | 1388 |
| LMArena Multi-Turn | — | 1418 |

## FAQ

### Is Codestral better than Longcat Flash Chat?

Longcat Flash Chat is the stronger model overall, scoring 42.1 to 30.6 on the Noometry Index.

### Is Codestral or Longcat Flash Chat better for coding?

Longcat Flash Chat scores higher on coding benchmarks: 43.5 versus 27.3 in the Noometry coding category.

### How many benchmarks do Codestral and Longcat Flash Chat share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Longcat Flash Chat has 19.