Model comparison
C4ai Aya Expanse 32b vs Codestral
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Cohere
Mistral AISummary
- The widest gap is in coding, where C4ai Aya Expanse 32b leads 34.8 to 27.3.
- Codestral accepts more context: 256K tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Codestral | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 35.9 | 30.6 |
| Released | 2024-10-24 | 2024-05-29 |
| Weights | Open | Proprietary |
| Context window | 128K | 256K |
| Max output | 4K | 8K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 18 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.8 (#231), Codestral: 27.3 (#321)
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| Aider Polyglot | — | 11.1% |
| BigCodeBench Instruct | — | 41.8% |
| LMArena Coding | 1197 | — |
| BigCodeBench Complete | — | 52.5% |
| ALE-Bench | — | 137.78 |
| HumanEval+ | — | 73.8% |
| MBPP+ | — | 61.9% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Codestral: 19.8 (#251)
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| Kagi LLM Benchmark | — | 32.5% |
| LMArena Hard Prompts | 1193 | — |
Math Not comparable
C4ai Aya Expanse 32b: 34.0 (#197), Codestral: —
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| LMArena Math | 1200 | — |
Knowledge Not comparable
C4ai Aya Expanse 32b: 33.2 (#206), Codestral: —
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.4 (#230), Codestral: —
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| LMArena Non-English | 1213 | — |
| LMArena Chinese | 1211 | — |
| LMArena French | 1248 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |
Instruction Following Not comparable
C4ai Aya Expanse 32b: 62.6 (#237), Codestral: —
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#220), Codestral: —
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.2 (#235), Codestral: —
| Benchmark | C4ai Aya Expanse 32b | Codestral |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Codestral?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 30.6 on the Noometry Index.
Is C4ai Aya Expanse 32b or Codestral better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 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 C4ai Aya Expanse 32b and Codestral share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Codestral has 7.