Model comparison
Dolly 2.0-12b vs Llama 2-7B
Llama 2-7B is the stronger model overall, scoring 29.1 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
MetaSummary
- They share 17 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Llama 2-7B in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 2-7B leads 28.0 to 15.2.
Side by side
| Dolly 2.0-12b | Llama 2-7B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 25.5 | 29.1 |
| Released | 2023-04-11 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-7B leads
Dolly 2.0-12b: 23.4 (#332), Llama 2-7B: 29.2 (#307)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| LMArena Coding | 776 | 1002 |
Reasoning Too close to call
Dolly 2.0-12b: 15.3 (#316), Llama 2-7B: 15.7 (#312)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1009 |
| Epoch Capabilities Index | 89.67 | 99.06 |
| HellaSwag | 70.8% | 77.2% |
| PIQA | 75.4% | 78.8% |
| WinoGrande | 61.8% | 69.2% |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | — | 39.2% |
| LAMBADA | — | 73.3% |
Math Llama 2-7B leads
Dolly 2.0-12b: 27.3 (#251), Llama 2-7B: 30.7 (#233)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| LMArena Math | 871 | 1042 |
| GSM8K | — | 16.7% |
Knowledge Not comparable
Dolly 2.0-12b: —, Llama 2-7B: 28.2 (#248)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 45.9% |
| BoolQ | 56.3% | 77.9% |
| MMLU | 26.2% | 45.8% |
| OpenBookQA | 39.2% | 58.6% |
| LMArena Expert | — | 1036 |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Dolly 2.0-12b: —, Llama 2-7B: —
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual Llama 2-7B leads
Dolly 2.0-12b: 17.4 (#296), Llama 2-7B: 23.8 (#293)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 836 | 973 |
| LMArena Chinese | 836 | 973 |
| LMArena French | — | 970 |
| LMArena German | — | 978 |
| LMArena Russian | — | 995 |
| LMArena Spanish | — | 1007 |
Instruction Following Llama 2-7B leads
Dolly 2.0-12b: 38.7 (#304), Llama 2-7B: 50.8 (#298)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 814 | 1006 |
Long Context Not comparable
Dolly 2.0-12b: —, Llama 2-7B: 30.4 (#287)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | — | 999 |
Writing & Preference Llama 2-7B leads
Dolly 2.0-12b: 15.2 (#311), Llama 2-7B: 28.0 (#298)
| Benchmark | Dolly 2.0-12b | Llama 2-7B |
|---|---|---|
| LMArena Text | 851 | 1053 |
| LMArena Creative Writing | 864 | 1033 |
| LMArena Multi-Turn | 740 | 1029 |
Frequently asked questions
Is Dolly 2.0-12b better than Llama 2-7B?
Llama 2-7B is the stronger model overall, scoring 29.1 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Llama 2-7B better for coding?
Llama 2-7B scores higher on coding benchmarks: 29.2 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Llama 2-7B share?
17 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Llama 2-7B has 29.