Model comparison
C4ai Aya Expanse 32b vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 35.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
CohereSummary
- They share 12 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 1 category and Mercury 2 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 42.2.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Mercury 2 | |
|---|---|---|
| Provider | Cohere | Inception |
| Noometry Index | 35.9 | 39.1 |
| Released | 2024-10-24 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 18 | 17 |
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), Mercury 2: 33.5 (#255)
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| LMArena Coding | 1197 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |
Reasoning Too close to call
C4ai Aya Expanse 32b: 23.3 (#180), Mercury 2: 23.8 (#170)
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1362 |
| CritPt | — | 0.8% |
Math Not comparable
C4ai Aya Expanse 32b: 34.0 (#197), Mercury 2: —
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| LMArena Math | 1200 | — |
Knowledge Mercury 2 leads
C4ai Aya Expanse 32b: 33.2 (#206), Mercury 2: 36.2 (#172)
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 12.3% |
| LMArena Expert | 1182 | 1358 |
Multilingual Mercury 2 leads
C4ai Aya Expanse 32b: 38.4 (#230), Mercury 2: 46.6 (#157)
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1213 | 1331 |
| LMArena Chinese | 1211 | 1417 |
| LMArena Russian | 1227 | 1304 |
| LMArena French | 1248 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Spanish | 1193 | — |
Instruction Following Mercury 2 leads
C4ai Aya Expanse 32b: 62.6 (#237), Mercury 2: 70.2 (#165)
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1329 |
Long Context Mercury 2 leads
C4ai Aya Expanse 32b: 37.2 (#220), Mercury 2: 40.5 (#154)
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1228 | 1330 |
Writing & Preference Mercury 2 leads
C4ai Aya Expanse 32b: 42.2 (#235), Mercury 2: 53.8 (#155)
| Benchmark | C4ai Aya Expanse 32b | Mercury 2 |
|---|---|---|
| LMArena Text | 1224 | 1355 |
| LMArena Creative Writing | 1200 | 1289 |
| LMArena Multi-Turn | 1190 | 1358 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Mercury 2 better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do C4ai Aya Expanse 32b and Mercury 2 share?
12 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Mercury 2 has 17.