Model comparison
Amazon Nova Pro vs C4ai Aya Expanse 32b
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 31.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
CohereSummary
- They share 18 benchmarks with published results for both. Amazon Nova Pro scores higher in 5 categories and C4ai Aya Expanse 32b in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where C4ai Aya Expanse 32b leads 33.2 to 27.4.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Amazon Nova Pro and 10.9% for C4ai Aya Expanse 32b.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | C4ai Aya Expanse 32b | |
|---|---|---|
| Provider | Amazon | Cohere |
| Noometry Index | 31.0 | 35.9 |
| Released | 2024-12-03 | 2024-10-24 |
| Weights | Proprietary | Open |
| Context window | 300K | 128K |
| Max output | 10K | 4K |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Pro: 35.1 (#229), C4ai Aya Expanse 32b: 34.8 (#231)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Coding | 1270 | 1197 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), C4ai Aya Expanse 32b: —
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning C4ai Aya Expanse 32b leads
Amazon Nova Pro: 20.0 (#243), C4ai Aya Expanse 32b: 23.3 (#180)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1193 |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |
Math C4ai Aya Expanse 32b leads
Amazon Nova Pro: 28.5 (#243), C4ai Aya Expanse 32b: 34.0 (#197)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Math | 1252 | 1200 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge C4ai Aya Expanse 32b leads
Amazon Nova Pro: 27.4 (#250), C4ai Aya Expanse 32b: 33.2 (#206)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 10.9% |
| LMArena Expert | 1211 | 1182 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), C4ai Aya Expanse 32b: —
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), C4ai Aya Expanse 32b: 38.4 (#230)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Non-English | 1234 | 1213 |
| LMArena Chinese | 1244 | 1211 |
| LMArena French | 1271 | 1248 |
| LMArena German | 1243 | 1199 |
| LMArena Japanese | 1200 | 1163 |
| LMArena Korean | 1203 | 1158 |
| LMArena Russian | 1240 | 1227 |
| LMArena Spanish | 1182 | 1193 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), C4ai Aya Expanse 32b: 62.6 (#237)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Instruction Following | 1235 | 1196 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Too close to call
Amazon Nova Pro: 38.1 (#205), C4ai Aya Expanse 32b: 37.2 (#220)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Longer Query | 1255 | 1228 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), C4ai Aya Expanse 32b: 42.2 (#235)
| Benchmark | Amazon Nova Pro | C4ai Aya Expanse 32b |
|---|---|---|
| LMArena Text | 1259 | 1224 |
| LMArena Creative Writing | 1212 | 1200 |
| LMArena Multi-Turn | 1246 | 1190 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than C4ai Aya Expanse 32b?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or C4ai Aya Expanse 32b better for coding?
They score almost the same on coding (35.1 vs 34.8); test both on your own repository before choosing.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 128K.
How many benchmarks do Amazon Nova Pro and C4ai Aya Expanse 32b share?
18 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and C4ai Aya Expanse 32b has 18.