Model comparison
DBRX vs Dolly 2.0-12b
DBRX is the stronger model overall, scoring 29.4 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
DatabricksSummary
- They share 9 benchmarks with published results for both. DBRX scores higher in 5 categories and Dolly 2.0-12b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where DBRX leads 57.5 to 38.7.
Side by side
| DBRX | Dolly 2.0-12b | |
|---|---|---|
| Provider | Databricks | Databricks |
| Noometry Index | 29.4 | 25.5 |
| Released | 2024-03-27 | 2023-04-11 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Dolly 2.0-12b: 23.4 (#332)
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| LMArena Coding | 1132 | 776 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Dolly 2.0-12b: 15.3 (#316)
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| LMArena Hard Prompts | 1113 | 804 |
| Epoch Capabilities Index | — | 89.67 |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |
Math Dolly 2.0-12b leads
DBRX: 24.3 (#269), Dolly 2.0-12b: 27.3 (#251)
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | 1145 | 871 |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
DBRX: 14.9 (#294), Dolly 2.0-12b: —
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| MMLU | — | 26.2% |
| OpenBookQA | — | 39.2% |
Multilingual DBRX leads
DBRX: 29.3 (#268), Dolly 2.0-12b: 17.4 (#296)
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | 1071 | 836 |
| LMArena Chinese | 1068 | 836 |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Russian | 1078 | — |
| LMArena Spanish | 1064 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Dolly 2.0-12b: 38.7 (#304)
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | 1112 | 814 |
Long Context Not comparable
DBRX: 33.7 (#258), Dolly 2.0-12b: —
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| LMArena Longer Query | 1112 | — |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Dolly 2.0-12b: 15.2 (#311)
| Benchmark | DBRX | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | 1119 | 851 |
| LMArena Creative Writing | 1104 | 864 |
| LMArena Multi-Turn | 1111 | 740 |
Frequently asked questions
Is DBRX better than Dolly 2.0-12b?
DBRX is the stronger model overall, scoring 29.4 to 25.5 on the Noometry Index.
Is DBRX or Dolly 2.0-12b better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 23.4 in the Noometry coding category.
How many benchmarks do DBRX and Dolly 2.0-12b share?
9 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Dolly 2.0-12b has 17.