Model comparison
C4ai Aya Expanse 32b vs Mistral Small 3
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 31.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Cohere
Mistral AISummary
- They share 16 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 5 categories and Mistral Small 3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where C4ai Aya Expanse 32b leads 34.0 to 16.3.
- C4ai Aya Expanse 32b accepts more context: 128K tokens versus 33K.
Side by side
| C4ai Aya Expanse 32b | Mistral Small 3 | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 35.9 | 31.2 |
| Released | 2024-10-24 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 128K | 33K |
| Max output | 4K | 16K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 18 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
C4ai Aya Expanse 32b: 34.8 (#231), Mistral Small 3: 36.5 (#207)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1197 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Mistral Small 3: 18.9 (#273)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |
Math C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.0 (#197), Mistral Small 3: 16.3 (#295)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1200 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
Knowledge C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 33.2 (#206), Mistral Small 3: 25.1 (#263)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1182 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 10.9% | — |
Multilingual C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 38.4 (#230), Mistral Small 3: 37.3 (#236)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1213 | 1198 |
| LMArena Chinese | 1211 | 1204 |
| LMArena French | 1248 | 1203 |
| LMArena German | 1199 | 1211 |
| LMArena Japanese | 1163 | 1111 |
| LMArena Korean | 1158 | 1188 |
| LMArena Russian | 1227 | 1216 |
| LMArena Spanish | 1193 | — |
Instruction Following Mistral Small 3 leads
C4ai Aya Expanse 32b: 62.6 (#237), Mistral Small 3: 63.7 (#229)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1214 |
Long Context Too close to call
C4ai Aya Expanse 32b: 37.2 (#220), Mistral Small 3: 37.8 (#211)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1228 | 1246 |
Writing & Preference C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 42.2 (#235), Mistral Small 3: 32.2 (#280)
| Benchmark | C4ai Aya Expanse 32b | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1224 | 1234 |
| LMArena Creative Writing | 1200 | 1195 |
| LMArena Multi-Turn | 1190 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Mistral Small 3?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 31.2 on the Noometry Index.
Is C4ai Aya Expanse 32b or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
C4ai Aya Expanse 32b does, with 128K tokens against 33K.
How many benchmarks do C4ai Aya Expanse 32b and Mistral Small 3 share?
16 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Mistral Small 3 has 24.