Model comparison
Dolly 2.0-12b vs ERNIE 5.1
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
Databricks
BaiduSummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and ERNIE 5.1 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.1 to 15.2.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Dolly 2.0-12b | ERNIE 5.1 | |
|---|---|---|
| Provider | Databricks | Baidu |
| Noometry Index | 25.5 | 43.8 |
| Released | 2023-04-11 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
Dolly 2.0-12b: 23.4 (#332), ERNIE 5.1: 44.0 (#76)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Coding | 776 | 1488 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, ERNIE 5.1: —
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning ERNIE 5.1 leads
Dolly 2.0-12b: 15.3 (#316), ERNIE 5.1: 21.9 (#211)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1481 |
| NYT Connections (extended) | — | 23.4% |
| Epoch Capabilities Index | 89.67 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math ERNIE 5.1 leads
Dolly 2.0-12b: 27.3 (#251), ERNIE 5.1: 40.3 (#92)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Math | 871 | 1481 |
Knowledge Not comparable
Dolly 2.0-12b: —, ERNIE 5.1: 41.9 (#102)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | — | 1492 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual ERNIE 5.1 leads
Dolly 2.0-12b: 17.4 (#296), ERNIE 5.1: 55.5 (#29)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | 836 | 1454 |
| LMArena Chinese | 836 | 1508 |
| LMArena French | — | 1488 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1427 |
| LMArena Russian | — | 1459 |
| LMArena Spanish | — | 1473 |
Instruction Following ERNIE 5.1 leads
Dolly 2.0-12b: 38.7 (#304), ERNIE 5.1: 76.7 (#37)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | 814 | 1460 |
Long Context Not comparable
Dolly 2.0-12b: —, ERNIE 5.1: 44.7 (#59)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | — | 1462 |
Writing & Preference ERNIE 5.1 leads
Dolly 2.0-12b: 15.2 (#311), ERNIE 5.1: 65.1 (#52)
| Benchmark | Dolly 2.0-12b | ERNIE 5.1 |
|---|---|---|
| LMArena Text | 851 | 1468 |
| LMArena Creative Writing | 864 | 1441 |
| LMArena Multi-Turn | 740 | 1471 |
Frequently asked questions
Is Dolly 2.0-12b better than ERNIE 5.1?
ERNIE 5.1 is the stronger model overall, scoring 43.8 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 44.0 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and ERNIE 5.1 share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and ERNIE 5.1 has 19.