Model comparison
Dolly 2.0-12b vs Llama 2-13B
Llama 2-13B is the stronger model overall, scoring 29.1 to 24.9 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 1 category and Llama 2-13B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 2-13B leads 30.0 to 15.3.
Side by side
| Dolly 2.0-12b | Llama 2-13B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 24.9 | 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 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Dolly 2.0-12b: 23.0 (#327), Llama 2-13B: 30.4 (#287)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| LMArena Coding | 776 | 1062 |
Reasoning Dolly 2.0-12b leads
Dolly 2.0-12b: 14.6 (#315), Llama 2-13B: 12.3 (#333)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1051 |
| Epoch Capabilities Index | 88.94 | 105.8 |
| HellaSwag | 70.8% | 80.7% |
| PIQA | 75.4% | 80.8% |
| WinoGrande | 61.8% | 72.8% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| LAMBADA | — | 76.5% |
Math Llama 2-13B leads
Dolly 2.0-12b: 25.0 (#250), Llama 2-13B: 28.7 (#226)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| LMArena Math | 871 | 1065 |
| GSM8K | — | 36.9% |
Knowledge Not comparable
Dolly 2.0-12b: —, Llama 2-13B: 27.5 (#244)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 60.3% |
| BoolQ | 56.3% | 82.4% |
| MMLU | 26.2% | 55.6% |
| OpenBookQA | 39.2% | 57% |
| LMArena Expert | — | 1030 |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Dolly 2.0-12b: —, Llama 2-13B: —
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Llama 2-13B leads
Dolly 2.0-12b: 17.4 (#291), Llama 2-13B: 26.7 (#274)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 836 | 1024 |
| LMArena Chinese | 836 | 1001 |
| LMArena French | — | 1043 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Russian | — | 1055 |
| LMArena Spanish | — | 1086 |
Instruction Following Llama 2-13B leads
Dolly 2.0-12b: 38.9 (#299), Llama 2-13B: 53.5 (#282)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 814 | 1046 |
Long Context Not comparable
Dolly 2.0-12b: —, Llama 2-13B: 32.3 (#264)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | — | 1064 |
Writing & Preference Llama 2-13B leads
Dolly 2.0-12b: 15.3 (#306), Llama 2-13B: 30.0 (#284)
| Benchmark | Dolly 2.0-12b | Llama 2-13B |
|---|---|---|
| LMArena Text | 851 | 1085 |
| LMArena Creative Writing | 864 | 1047 |
| LMArena Multi-Turn | 740 | 1050 |
Frequently asked questions
Is Dolly 2.0-12b better than Llama 2-13B?
Llama 2-13B is the stronger model overall, scoring 29.1 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Llama 2-13B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.4 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Llama 2-13B share?
17 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Llama 2-13B has 32.