Model comparison
C4ai Aya Expanse 32b vs Devstral Small 2505
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Cohere
Mistral AISummary
- The widest gap is in coding, where Devstral Small 2505 leads 38.9 to 34.8.
Side by side
| C4ai Aya Expanse 32b | Devstral Small 2505 | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 35.9 | 34.3 |
| Released | 2024-10-24 | 2025-05-07 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 18 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
C4ai Aya Expanse 32b: 34.8 (#231), Devstral Small 2505: 38.9 (#166)
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 56.4% |
| SciCode | — | 28.8% |
| LMArena Coding | 1197 | — |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Devstral Small 2505: 19.7 (#252)
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| Kagi LLM Benchmark | — | 37.7% |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1193 | — |
Math Not comparable
C4ai Aya Expanse 32b: 34.0 (#197), Devstral Small 2505: —
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| LMArena Math | 1200 | — |
Knowledge Not comparable
C4ai Aya Expanse 32b: 33.2 (#206), Devstral Small 2505: —
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.4 (#230), Devstral Small 2505: —
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| 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), Devstral Small 2505: —
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#220), Devstral Small 2505: —
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.2 (#235), Devstral Small 2505: —
| Benchmark | C4ai Aya Expanse 32b | Devstral Small 2505 |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Devstral Small 2505?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 34.3 on the Noometry Index.
Is C4ai Aya Expanse 32b or Devstral Small 2505 better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do C4ai Aya Expanse 32b and Devstral Small 2505 share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Devstral Small 2505 has 4.