Model comparison
Codestral vs GLM-4.6V
GLM-4.6V is the stronger model overall, scoring 41.3 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in coding, where GLM-4.6V leads 40.9 to 27.3.
- Both cost about the same: $0.30 input and $0.90 output per million tokens.
- Codestral accepts more context: 256K tokens versus 128K.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| Codestral | GLM-4.6V | |
|---|---|---|
| Provider | Mistral AI | Z.ai (Zhipu) |
| Noometry Index | 30.6 | 41.3 |
| Released | 2024-05-29 | 2025-12-08 |
| Weights | Proprietary | Open |
| Context window | 256K | 128K |
| Max output | 8K | 33K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $0.90 | $0.90 |
| Results tracked | 7 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
Codestral: 27.3 (#321), GLM-4.6V: 40.9 (#128)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1390 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning GLM-4.6V leads
Codestral: 19.8 (#251), GLM-4.6V: 27.6 (#115)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1368 |
Knowledge Not comparable
Codestral: —, GLM-4.6V: 38.0 (#149)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| LMArena Expert | — | 1371 |
Multimodal Not comparable
Codestral: —, GLM-4.6V: 34.8 (#90)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |
Multilingual Not comparable
Codestral: —, GLM-4.6V: 48.6 (#141)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| LMArena Non-English | — | 1359 |
| LMArena Chinese | — | 1425 |
| LMArena Russian | — | 1340 |
Instruction Following Not comparable
Codestral: —, GLM-4.6V: 71.4 (#151)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | — | 1352 |
Long Context Not comparable
Codestral: —, GLM-4.6V: 41.3 (#143)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | — | 1358 |
Writing & Preference Not comparable
Codestral: —, GLM-4.6V: 56.6 (#137)
| Benchmark | Codestral | GLM-4.6V |
|---|---|---|
| LMArena Text | — | 1377 |
| LMArena Creative Writing | — | 1347 |
| LMArena Multi-Turn | — | 1360 |
Frequently asked questions
Is Codestral better than GLM-4.6V?
GLM-4.6V is the stronger model overall, scoring 41.3 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or GLM-4.6V?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or GLM-4.6V better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.9 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Codestral does, with 256K tokens against 128K.
How many benchmarks do Codestral and GLM-4.6V share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and GLM-4.6V has 12.