Model comparison
ERNIE 5.1 vs Hy3
ERNIE 5.1 and Hy3 score almost the same on the Noometry Index (43.8 vs 44.2), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
Baidu
TencentSummary
- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 6 categories and Hy3 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 26.1 to 21.9.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 41.2% for Hy3.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Hy3 | |
|---|---|---|
| Provider | Baidu | Tencent |
| Noometry Index | 43.8 | 44.2 |
| Released | — | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 19 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
ERNIE 5.1: 44.0 (#76), Hy3: 46.8 (#63)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Coding | 1488 | 1464 |
| LMArena WebDev | — | 1508 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Hy3: —
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Hy3 leads
ERNIE 5.1: 21.9 (#211), Hy3: 26.1 (#136)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 23.4% | 41.2% |
| LMArena Hard Prompts | 1481 | 1447 |
Math Too close to call
ERNIE 5.1: 40.3 (#92), Hy3: 40.1 (#93)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Math | 1481 | 1475 |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Hy3: 40.8 (#114)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Expert | 1492 | 1460 |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Hy3: 53.5 (#65)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Non-English | 1454 | 1426 |
| LMArena Chinese | 1508 | 1493 |
| LMArena French | 1488 | 1461 |
| LMArena German | 1470 | 1439 |
| LMArena Japanese | 1422 | 1392 |
| LMArena Korean | 1427 | 1395 |
| LMArena Russian | 1459 | 1432 |
| LMArena Spanish | 1473 | 1456 |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Hy3: 75.1 (#70)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1426 |
Long Context Too close to call
ERNIE 5.1: 44.7 (#59), Hy3: 44.1 (#75)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1462 | 1442 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Hy3: 62.2 (#81)
| Benchmark | ERNIE 5.1 | Hy3 |
|---|---|---|
| LMArena Text | 1468 | 1439 |
| LMArena Creative Writing | 1441 | 1402 |
| LMArena Multi-Turn | 1471 | 1436 |
Frequently asked questions
Is ERNIE 5.1 better than Hy3?
ERNIE 5.1 and Hy3 score almost the same on the Noometry Index (43.8 vs 44.2), so choose on price, context window or the category you care about most.
Is ERNIE 5.1 or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 44.0 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Hy3 share?
18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Hy3 has 19.