Model comparison
C4ai Aya Expanse 8b vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 34.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Cohere
TencentSummary
- They share 14 benchmarks with published results for both. C4ai Aya Expanse 8b 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 62.2 to 39.0.
Side by side
| C4ai Aya Expanse 8b | Hy3 | |
|---|---|---|
| Provider | Cohere | Tencent |
| Noometry Index | 34.9 | 44.2 |
| Released | — | 2026-07-06 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 15 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
C4ai Aya Expanse 8b: 33.8 (#252), Hy3: 46.8 (#63)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Coding | 1160 | 1464 |
| LMArena WebDev | — | 1508 |
Reasoning Hy3 leads
C4ai Aya Expanse 8b: 22.4 (#197), Hy3: 26.1 (#136)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1447 |
| NYT Connections (extended) | — | 41.2% |
Math Hy3 leads
C4ai Aya Expanse 8b: 33.3 (#203), Hy3: 40.1 (#93)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Math | 1168 | 1475 |
Knowledge Hy3 leads
C4ai Aya Expanse 8b: 33.6 (#201), Hy3: 40.8 (#114)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Expert | 1153 | 1460 |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual Hy3 leads
C4ai Aya Expanse 8b: 36.1 (#242), Hy3: 53.5 (#65)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Non-English | 1180 | 1426 |
| LMArena Chinese | 1181 | 1493 |
| LMArena German | 1188 | 1439 |
| LMArena Japanese | 1120 | 1392 |
| LMArena Russian | 1197 | 1432 |
| LMArena French | — | 1461 |
| LMArena Korean | — | 1395 |
| LMArena Spanish | — | 1456 |
Instruction Following Hy3 leads
C4ai Aya Expanse 8b: 60.1 (#253), Hy3: 75.1 (#70)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1155 | 1426 |
Long Context Hy3 leads
C4ai Aya Expanse 8b: 36.1 (#236), Hy3: 44.1 (#75)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Longer Query | 1191 | 1442 |
Writing & Preference Hy3 leads
C4ai Aya Expanse 8b: 39.0 (#250), Hy3: 62.2 (#81)
| Benchmark | C4ai Aya Expanse 8b | Hy3 |
|---|---|---|
| LMArena Text | 1185 | 1439 |
| LMArena Creative Writing | 1168 | 1402 |
| LMArena Multi-Turn | 1160 | 1436 |
Frequently asked questions
Is C4ai Aya Expanse 8b better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 34.9 on the Noometry Index.
Is C4ai Aya Expanse 8b or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 33.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 8b and Hy3 share?
14 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and Hy3 has 19.