Model comparison
Dolly 2.0-12b vs Llama 2-70B
Dolly 2.0-12b is the stronger model overall, scoring 25.5 to 24.4 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 2 categories and Llama 2-70B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Dolly 2.0-12b leads 27.3 to 8.1.
Side by side
| Dolly 2.0-12b | Llama 2-70B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 25.5 | 24.4 |
| Released | 2023-04-11 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-70B leads
Dolly 2.0-12b: 23.4 (#332), Llama 2-70B: 31.4 (#286)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| LMArena Coding | 776 | 1079 |
Reasoning Too close to call
Dolly 2.0-12b: 15.3 (#316), Llama 2-70B: 14.4 (#325)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1073 |
| Epoch Capabilities Index | 89.67 | 113.79 |
| HellaSwag | 70.8% | 85.3% |
| PIQA | 75.4% | 82.8% |
| WinoGrande | 61.8% | 80.2% |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| LAMBADA | — | 78.9% |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), Llama 2-70B: 8.1 (#326)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| LMArena Math | 871 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Not comparable
Dolly 2.0-12b: —, Llama 2-70B: 7.4 (#310)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 78.3% |
| BoolQ | 56.3% | 88.6% |
| MMLU | 26.2% | 69.9% |
| OpenBookQA | 39.2% | 60.2% |
| GPQA Diamond | — | 26.3% |
| LMArena Expert | — | 1039 |
| TriviaQA | — | 87.6% |
Multilingual Llama 2-70B leads
Dolly 2.0-12b: 17.4 (#296), Llama 2-70B: 27.7 (#274)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 836 | 1045 |
| LMArena Chinese | 836 | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |
Instruction Following Llama 2-70B leads
Dolly 2.0-12b: 38.7 (#304), Llama 2-70B: 54.9 (#278)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 814 | 1071 |
Long Context Not comparable
Dolly 2.0-12b: —, Llama 2-70B: 32.3 (#270)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | — | 1062 |
Writing & Preference Llama 2-70B leads
Dolly 2.0-12b: 15.2 (#311), Llama 2-70B: 32.3 (#279)
| Benchmark | Dolly 2.0-12b | Llama 2-70B |
|---|---|---|
| LMArena Text | 851 | 1115 |
| LMArena Creative Writing | 864 | 1075 |
| LMArena Multi-Turn | 740 | 1088 |
Frequently asked questions
Is Dolly 2.0-12b better than Llama 2-70B?
Dolly 2.0-12b is the stronger model overall, scoring 25.5 to 24.4 on the Noometry Index.
Is Dolly 2.0-12b or Llama 2-70B better for coding?
Llama 2-70B scores higher on coding benchmarks: 31.4 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Llama 2-70B share?
17 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Llama 2-70B has 35.