Model comparison
C4ai Aya Expanse 32b vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.7 to 35.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
CohereSummary
- They share 18 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Nova 2 Lite in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nova 2 Lite leads 53.9 to 42.2.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 10.9% for C4ai Aya Expanse 32b and 5.1% for Nova 2 Lite.
- Nova 2 Lite accepts more context: 1M tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Nova 2 Lite | |
|---|---|---|
| Provider | Cohere | Amazon |
| Noometry Index | 35.9 | 39.7 |
| Released | 2024-10-24 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 18 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
C4ai Aya Expanse 32b: 34.8 (#231), Nova 2 Lite: 40.7 (#134)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1197 | 1385 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, Nova 2 Lite: 24.1 (#121)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Nova 2 Lite leads
C4ai Aya Expanse 32b: 23.3 (#180), Nova 2 Lite: 27.5 (#118)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1364 |
Math Nova 2 Lite leads
C4ai Aya Expanse 32b: 34.0 (#197), Nova 2 Lite: 37.5 (#156)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1200 | 1359 |
Knowledge Nova 2 Lite leads
C4ai Aya Expanse 32b: 33.2 (#206), Nova 2 Lite: 43.0 (#94)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 5.1% |
| LMArena Expert | 1182 | 1358 |
Multilingual Nova 2 Lite leads
C4ai Aya Expanse 32b: 38.4 (#230), Nova 2 Lite: 47.1 (#153)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1213 | 1337 |
| LMArena Chinese | 1211 | 1364 |
| LMArena French | 1248 | 1381 |
| LMArena German | 1199 | 1343 |
| LMArena Japanese | 1163 | 1271 |
| LMArena Korean | 1158 | 1284 |
| LMArena Russian | 1227 | 1343 |
| LMArena Spanish | 1193 | 1373 |
Instruction Following Nova 2 Lite leads
C4ai Aya Expanse 32b: 62.6 (#237), Nova 2 Lite: 70.5 (#161)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1196 | 1335 |
Long Context Nova 2 Lite leads
C4ai Aya Expanse 32b: 37.2 (#220), Nova 2 Lite: 40.6 (#150)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1228 | 1335 |
Writing & Preference Nova 2 Lite leads
C4ai Aya Expanse 32b: 42.2 (#235), Nova 2 Lite: 53.9 (#154)
| Benchmark | C4ai Aya Expanse 32b | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1224 | 1362 |
| LMArena Creative Writing | 1200 | 1291 |
| LMArena Multi-Turn | 1190 | 1338 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Nova 2 Lite share?
18 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Nova 2 Lite has 19.