Model comparison
Dolly 2.0-12b vs ERNIE 5.0 0110
ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 24.9 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 5.0 0110 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.4 to 15.3.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Dolly 2.0-12b | ERNIE 5.0 0110 | |
|---|---|---|
| Provider | Databricks | Baidu |
| Noometry Index | 24.9 | 41.2 |
| Released | 2023-04-11 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.0 0110 leads
Dolly 2.0-12b: 23.0 (#327), ERNIE 5.0 0110: 42.3 (#94)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Coding | 776 | 1455 |
Reasoning ERNIE 5.0 0110 leads
Dolly 2.0-12b: 14.6 (#315), ERNIE 5.0 0110: 16.3 (#296)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1446 |
| NYT Connections (extended) | — | 10.3% |
| Thematic Generalization | — | 41.7% |
| Epoch Capabilities Index | 88.94 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math ERNIE 5.0 0110 leads
Dolly 2.0-12b: 25.0 (#250), ERNIE 5.0 0110: 36.5 (#111)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Math | 871 | 1437 |
Knowledge Not comparable
Dolly 2.0-12b: —, ERNIE 5.0 0110: 39.2 (#125)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Expert | — | 1427 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multimodal Not comparable
Dolly 2.0-12b: —, ERNIE 5.0 0110: 39.1 (#49)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Vision | — | 1248 |
Multilingual ERNIE 5.0 0110 leads
Dolly 2.0-12b: 17.4 (#291), ERNIE 5.0 0110: 54.3 (#47)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Non-English | 836 | 1436 |
| LMArena Chinese | 836 | 1512 |
| LMArena French | — | 1466 |
| LMArena German | — | 1462 |
| LMArena Japanese | — | 1383 |
| LMArena Korean | — | 1406 |
| LMArena Russian | — | 1446 |
| LMArena Spanish | — | 1473 |
Instruction Following ERNIE 5.0 0110 leads
Dolly 2.0-12b: 38.9 (#299), ERNIE 5.0 0110: 74.7 (#88)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Instruction Following | 814 | 1413 |
Long Context Not comparable
Dolly 2.0-12b: —, ERNIE 5.0 0110: 43.4 (#90)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Longer Query | — | 1422 |
Writing & Preference ERNIE 5.0 0110 leads
Dolly 2.0-12b: 15.3 (#306), ERNIE 5.0 0110: 63.4 (#64)
| Benchmark | Dolly 2.0-12b | ERNIE 5.0 0110 |
|---|---|---|
| LMArena Text | 851 | 1445 |
| LMArena Creative Writing | 864 | 1426 |
| LMArena Multi-Turn | 740 | 1433 |
Frequently asked questions
Is Dolly 2.0-12b better than ERNIE 5.0 0110?
ERNIE 5.0 0110 is the stronger model overall, scoring 41.2 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or ERNIE 5.0 0110 better for coding?
ERNIE 5.0 0110 scores higher on coding benchmarks: 42.3 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and ERNIE 5.0 0110 share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and ERNIE 5.0 0110 has 20.