Model comparison
C4ai Aya Expanse 32b vs Hy3
Hy3 is the stronger model overall, scoring 43.6 to 35.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Cohere
TencentSummary
- They share 15 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 42.4.
- Hy3 accepts more context: 262K tokens versus 128K.
Side by side
| C4ai Aya Expanse 32b | Hy3 | |
|---|---|---|
| Provider | Cohere | Tencent |
| Noometry Index | 35.3 | 43.6 |
| Released | 2024-10-24 | 2026-07-06 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 128K |
| Input $ / M tokens | — | $0.13 |
| Output $ / M tokens | — | $0.53 |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
C4ai Aya Expanse 32b: 34.3 (#227), Hy3: 46.6 (#60)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Coding | 1197 | 1465 |
| LMArena WebDev | — | 1509 |
Reasoning Hy3 leads
C4ai Aya Expanse 32b: 22.3 (#183), Hy3: 25.0 (#134)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1449 |
| NYT Connections (extended) | — | 41.2% |
Math Hy3 leads
C4ai Aya Expanse 32b: 31.4 (#195), Hy3: 37.4 (#98)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Math | 1200 | 1475 |
Knowledge Hy3 leads
C4ai Aya Expanse 32b: 32.6 (#202), Hy3: 40.2 (#108)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Expert | 1182 | 1461 |
| Vectara Hallucination Rate | 10.9% | — |
Multilingual Hy3 leads
C4ai Aya Expanse 32b: 38.5 (#225), Hy3: 53.7 (#60)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Non-English | 1213 | 1427 |
| LMArena Chinese | 1210 | 1496 |
| LMArena French | 1247 | 1461 |
| LMArena Korean | 1158 | 1390 |
| LMArena Russian | 1227 | 1435 |
| LMArena Spanish | 1193 | 1448 |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
Instruction Following Hy3 leads
C4ai Aya Expanse 32b: 62.9 (#232), Hy3: 75.3 (#68)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1425 |
Long Context Hy3 leads
C4ai Aya Expanse 32b: 37.2 (#215), Hy3: 44.1 (#70)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Longer Query | 1228 | 1443 |
Writing & Preference Hy3 leads
C4ai Aya Expanse 32b: 42.4 (#230), Hy3: 62.5 (#75)
| Benchmark | C4ai Aya Expanse 32b | Hy3 |
|---|---|---|
| LMArena Text | 1224 | 1442 |
| LMArena Creative Writing | 1200 | 1399 |
| LMArena Multi-Turn | 1190 | 1436 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Hy3?
Hy3 is the stronger model overall, scoring 43.6 to 35.3 on the Noometry Index.
Is C4ai Aya Expanse 32b or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Hy3 share?
15 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Hy3 has 17.