Model comparison
C4ai Aya Expanse 32b vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 35.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Cohere
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 42.2.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Sonar | |
|---|---|---|
| Provider | Cohere | Perplexity |
| Noometry Index | 35.9 | 38.5 |
| Released | 2024-10-24 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 18 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
C4ai Aya Expanse 32b: 34.8 (#231), Sonar: 35.7 (#221)
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1197 | — |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Sonar: 21.1 (#227)
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1193 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Too close to call
C4ai Aya Expanse 32b: 34.0 (#197), Sonar: 33.7 (#200)
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1200 | — |
Knowledge Not comparable
C4ai Aya Expanse 32b: 33.2 (#206), Sonar: —
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.4 (#230), Sonar: —
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| 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 Sonar leads
C4ai Aya Expanse 32b: 62.6 (#237), Sonar: 71.4 (#150)
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#220), Sonar: —
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Sonar leads
C4ai Aya Expanse 32b: 42.2 (#235), Sonar: 52.6 (#167)
| Benchmark | C4ai Aya Expanse 32b | Sonar |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Sonar better for coding?
They score almost the same on coding (34.8 vs 35.7); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do C4ai Aya Expanse 32b and Sonar share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Sonar has 7.