# Codestral vs GLM-5.3-Flash

> GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 30.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-glm-5-3-flash
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and GLM-5.3-Flash in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5.3-Flash leads 53.7 to 26.9.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- GLM-5.3-Flash accepts more context: 1M tokens versus 256K.

## Snapshot

| | Codestral | GLM-5.3-Flash |
|---|---|---|
| Provider | Mistral AI | Z.ai (Zhipu) |
| Noometry Index | 30.1 | 49.6 |
| Rank | 287 | 45 |
| Context | 256K | 1M |
| Input $/M | $0.30 | $0.15 |
| Output $/M | $0.90 | $0.50 |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- GLM-5.3-Flash: 53.7 (#26)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| ALE-Bench | 137.78 | 303.55 |
| DeepSWE | — | 63.4% |
| FrontierCode | — | 31.8% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1614 |
| SciCode | — | 51.6% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1506 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- GLM-5.3-Flash: 34.3 (#41)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| APEX-Agents | — | 52.8% |
| GDP.pdf | — | 14% |

## Reasoning

- Codestral: 19.1 (#244)
- GLM-5.3-Flash: 31.7 (#69)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 15.4% |
| Chess Puzzles | — | 14% |
| LMArena Hard Prompts | — | 1490 |
| Mystery Game Puzzles | — | 8% |
| Surface Evolver Bench | — | 52.5% |
| Bench to the Future 3 | — | 0.15 |
| Epoch Capabilities Index | — | 151.9 |

## Math

- Codestral: —
- GLM-5.3-Flash: 53.1 (#38)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 93.9% |
| ProofBench | — | 21% |
| LMArena Math | — | 1499 |

## Knowledge

- Codestral: —
- GLM-5.3-Flash: 58.4 (#33)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| GPQA Diamond | — | 90.2% |
| LMArena Expert | — | 1512 |

## Multimodal

- Codestral: —
- GLM-5.3-Flash: 42.6 (#25)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| LMArena Vision | — | 1304 |

## Multilingual

- Codestral: —
- GLM-5.3-Flash: 56.2 (#24)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| LMArena Non-English | — | 1462 |
| LMArena Chinese | — | 1529 |
| LMArena French | — | 1495 |
| LMArena German | — | 1457 |
| LMArena Japanese | — | 1420 |
| LMArena Korean | — | 1443 |
| LMArena Russian | — | 1472 |
| LMArena Spanish | — | 1471 |

## Instruction Following

- Codestral: —
- GLM-5.3-Flash: 77.8 (#17)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| LMArena Instruction Following | — | 1480 |

## Long Context

- Codestral: —
- GLM-5.3-Flash: 45.3 (#41)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| LMArena Longer Query | — | 1479 |

## Writing & Preference

- Codestral: —
- GLM-5.3-Flash: 65.4 (#49)

| Benchmark | Codestral | GLM-5.3-Flash |
|---|---|---|
| LMArena Text | — | 1471 |
| LMArena Creative Writing | — | 1440 |
| LMArena Multi-Turn | — | 1471 |

## FAQ

### Is Codestral better than GLM-5.3-Flash?

GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 30.1 on the Noometry Index.

### Which is cheaper, Codestral or GLM-5.3-Flash?

GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Codestral lists at $0.30 and $0.90.

### Is Codestral or GLM-5.3-Flash better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.3-Flash does, with 1M tokens against 256K.

### How many benchmarks do Codestral and GLM-5.3-Flash share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and GLM-5.3-Flash has 36.