Model comparison
ERNIE 5.0 0110 vs Hy3
Hy3 is the stronger model overall, scoring 43.6 to 41.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Baidu
TencentSummary
- They share 16 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 2 categories and Hy3 in 6 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 25.0 to 16.3.
- The biggest single-benchmark swing is NYT Connections (extended): 10.3% for ERNIE 5.0 0110 and 41.2% for Hy3.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.0 0110 | Hy3 | |
|---|---|---|
| Provider | Baidu | Tencent |
| Noometry Index | 41.2 | 43.6 |
| Released | — | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.13 |
| Output $ / M tokens | — | $0.53 |
| Results tracked | 20 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
ERNIE 5.0 0110: 42.3 (#94), Hy3: 46.6 (#60)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Coding | 1455 | 1465 |
| LMArena WebDev | — | 1509 |
Reasoning Hy3 leads
ERNIE 5.0 0110: 16.3 (#296), Hy3: 25.0 (#134)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 10.3% | 41.2% |
| LMArena Hard Prompts | 1446 | 1449 |
| Thematic Generalization | 41.7% | — |
Math Too close to call
ERNIE 5.0 0110: 36.5 (#111), Hy3: 37.4 (#98)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Math | 1437 | 1475 |
Knowledge Hy3 leads
ERNIE 5.0 0110: 39.2 (#125), Hy3: 40.2 (#108)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Expert | 1427 | 1461 |
Multimodal Not comparable
ERNIE 5.0 0110: 39.1 (#49), Hy3: —
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Vision | 1248 | — |
Multilingual Too close to call
ERNIE 5.0 0110: 54.3 (#47), Hy3: 53.7 (#60)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Non-English | 1436 | 1427 |
| LMArena Chinese | 1512 | 1496 |
| LMArena French | 1466 | 1461 |
| LMArena Korean | 1406 | 1390 |
| LMArena Russian | 1446 | 1435 |
| LMArena Spanish | 1473 | 1448 |
| LMArena German | 1462 | — |
| LMArena Japanese | 1383 | — |
Instruction Following Too close to call
ERNIE 5.0 0110: 74.7 (#88), Hy3: 75.3 (#68)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1413 | 1425 |
Long Context Too close to call
ERNIE 5.0 0110: 43.4 (#90), Hy3: 44.1 (#70)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1443 |
Writing & Preference Too close to call
ERNIE 5.0 0110: 63.4 (#64), Hy3: 62.5 (#75)
| Benchmark | ERNIE 5.0 0110 | Hy3 |
|---|---|---|
| LMArena Text | 1445 | 1442 |
| LMArena Creative Writing | 1426 | 1399 |
| LMArena Multi-Turn | 1433 | 1436 |
Frequently asked questions
Is ERNIE 5.0 0110 better than Hy3?
Hy3 is the stronger model overall, scoring 43.6 to 41.2 on the Noometry Index.
Is ERNIE 5.0 0110 or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 42.3 in the Noometry coding category.
How many benchmarks do ERNIE 5.0 0110 and Hy3 share?
16 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Hy3 has 17.