Model comparison
C4ai Aya Expanse 32b vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 35.9 on the Noometry Index.
Last verified . 8 shared benchmarks.
CohereSummary
- They share 8 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 1 category and Mercury in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where C4ai Aya Expanse 32b leads 23.3 to 17.5.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Mercury | |
|---|---|---|
| Provider | Cohere | Inception |
| Noometry Index | 35.9 | 37.6 |
| Released | 2024-10-24 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
C4ai Aya Expanse 32b: 34.8 (#231), Mercury: 38.7 (#170)
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| LMArena Coding | 1197 | 1322 |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Mercury: 17.5 (#293)
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
Math Not comparable
C4ai Aya Expanse 32b: 34.0 (#197), Mercury: —
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| LMArena Math | 1200 | — |
Knowledge Not comparable
C4ai Aya Expanse 32b: 33.2 (#206), Mercury: —
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
Multilingual Mercury leads
C4ai Aya Expanse 32b: 38.4 (#230), Mercury: 41.6 (#206)
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| LMArena Non-English | 1213 | 1260 |
| LMArena Chinese | 1211 | — |
| LMArena French | 1248 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |
Instruction Following Mercury leads
C4ai Aya Expanse 32b: 62.6 (#237), Mercury: 65.2 (#224)
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| LMArena Instruction Following | 1196 | 1239 |
Long Context Mercury leads
C4ai Aya Expanse 32b: 37.2 (#220), Mercury: 38.4 (#198)
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| LMArena Longer Query | 1228 | 1266 |
Writing & Preference Mercury leads
C4ai Aya Expanse 32b: 42.2 (#235), Mercury: 46.2 (#221)
| Benchmark | C4ai Aya Expanse 32b | Mercury |
|---|---|---|
| LMArena Text | 1224 | 1282 |
| LMArena Creative Writing | 1200 | 1191 |
| LMArena Multi-Turn | 1190 | 1282 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 34.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Mercury share?
8 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Mercury has 9.