Model comparison
Codestral vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AISummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and GLM-4.5-Air in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-4.5-Air leads 33.3 to 27.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 43% for GLM-4.5-Air.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 131K.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| Codestral | GLM-4.5-Air | |
|---|---|---|
| Provider | Mistral AI | Z.ai (Zhipu) |
| Noometry Index | 30.6 | 38.9 |
| Released | 2024-05-29 | 2025-07-20 |
| Weights | Proprietary | Open |
| Context window | 256K | 131K |
| Max output | 8K | 98K |
| Input $ / M tokens | $0.30 | $0.20 |
| Output $ / M tokens | $0.90 | $1.10 |
| Results tracked | 7 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
Codestral: 27.3 (#321), GLM-4.5-Air: 33.3 (#259)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| GSO | — | 2.9% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1397 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning GLM-4.5-Air leads
Codestral: 19.8 (#251), GLM-4.5-Air: 24.1 (#166)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 43% |
| LMArena Hard Prompts | — | 1379 |
| ForecastBench | — | 59.2 |
Math Not comparable
Codestral: —, GLM-4.5-Air: 36.2 (#170)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| Omni-MATH | — | 39.1% |
| LMArena Math | — | 1396 |
Knowledge Not comparable
Codestral: —, GLM-4.5-Air: 35.0 (#191)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1370 |
Multilingual Not comparable
Codestral: —, GLM-4.5-Air: 49.1 (#135)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | — | 1366 |
| LMArena Chinese | — | 1426 |
| LMArena French | — | 1399 |
| LMArena German | — | 1377 |
| LMArena Japanese | — | 1348 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1373 |
| LMArena Spanish | — | 1386 |
Instruction Following Not comparable
Codestral: —, GLM-4.5-Air: 69.6 (#171)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| IFEval | — | 81.2% |
| LMArena Instruction Following | — | 1354 |
Long Context Not comparable
Codestral: —, GLM-4.5-Air: 41.6 (#135)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | — | 1366 |
Writing & Preference Not comparable
Codestral: —, GLM-4.5-Air: 55.9 (#139)
| Benchmark | Codestral | GLM-4.5-Air |
|---|---|---|
| LMArena Text | — | 1384 |
| LMArena Creative Writing | — | 1343 |
| WildBench | — | 78.9% |
| LMArena Multi-Turn | — | 1371 |
Frequently asked questions
Is Codestral better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or GLM-4.5-Air?
GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or GLM-4.5-Air better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Codestral does, with 256K tokens against 131K.
How many benchmarks do Codestral and GLM-4.5-Air share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and GLM-4.5-Air has 27.