Model comparison
ERNIE 5.1 vs Granite 4.0 H Small
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 36.5 on the Noometry Index.
Last verified . 13 shared benchmarks.
BaiduSummary
- They share 13 benchmarks with published results for both. ERNIE 5.1 scores higher in 7 categories and Granite 4.0 H Small in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 43.8.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.1 | Granite 4.0 H Small | |
|---|---|---|
| Provider | Baidu | IBM |
| Noometry Index | 43.8 | 36.5 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
ERNIE 5.1: 44.0 (#76), Granite 4.0 H Small: 36.4 (#209)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1488 | 1249 |
Agentic & Tool Use Not comparable
ERNIE 5.1: —, Granite 4.0 H Small: —
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Search | 1227 | — |
Reasoning Granite 4.0 H Small leads
ERNIE 5.1: 21.9 (#211), Granite 4.0 H Small: 24.4 (#163)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1240 |
| NYT Connections (extended) | 23.4% | — |
Math ERNIE 5.1 leads
ERNIE 5.1: 40.3 (#92), Granite 4.0 H Small: 31.4 (#223)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1481 | 1247 |
| Omni-MATH | — | 29.6% |
Knowledge ERNIE 5.1 leads
ERNIE 5.1: 41.9 (#102), Granite 4.0 H Small: 32.0 (#215)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1492 | 1251 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
Multilingual ERNIE 5.1 leads
ERNIE 5.1: 55.5 (#29), Granite 4.0 H Small: 38.6 (#228)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1454 | 1216 |
| LMArena Chinese | 1508 | 1249 |
| LMArena Russian | 1459 | 1201 |
| LMArena Spanish | 1473 | 1258 |
| LMArena French | 1488 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1427 | — |
Instruction Following ERNIE 5.1 leads
ERNIE 5.1: 76.7 (#37), Granite 4.0 H Small: 68.7 (#183)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1460 | 1222 |
| IFEval | — | 89% |
Long Context ERNIE 5.1 leads
ERNIE 5.1: 44.7 (#59), Granite 4.0 H Small: 37.7 (#213)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1462 | 1242 |
Writing & Preference ERNIE 5.1 leads
ERNIE 5.1: 65.1 (#52), Granite 4.0 H Small: 43.8 (#227)
| Benchmark | ERNIE 5.1 | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1468 | 1241 |
| LMArena Creative Writing | 1441 | 1211 |
| LMArena Multi-Turn | 1471 | 1242 |
| WildBench | — | 73.9% |
Frequently asked questions
Is ERNIE 5.1 better than Granite 4.0 H Small?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 36.5 on the Noometry Index.
Is ERNIE 5.1 or Granite 4.0 H Small better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 36.4 in the Noometry coding category.
How many benchmarks do ERNIE 5.1 and Granite 4.0 H Small share?
13 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Granite 4.0 H Small has 19.