Model comparison
Dolly 2.0-12b vs Llama 3-70B
Llama 3-70B is the stronger model overall, scoring 28.5 to 24.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Databricks
MetaSummary
- They share 12 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and Llama 3-70B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3-70B leads 43.0 to 15.3.
Side by side
| Dolly 2.0-12b | Llama 3-70B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 24.9 | 28.5 |
| Released | 2023-04-11 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Dolly 2.0-12b: 23.0 (#327), Llama 3-70B: 35.3 (#215)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| LMArena Coding | 776 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Llama 3-70B: 20.9 (#132)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Llama 3-70B leads
Dolly 2.0-12b: 14.6 (#315), Llama 3-70B: 17.4 (#284)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1195 |
| Epoch Capabilities Index | 88.94 | 122.91 |
| WinoGrande | 61.8% | 83.5% |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| ForecastBench | — | 57.1 |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 25.0 (#250), Llama 3-70B: 12.0 (#299)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| LMArena Math | 871 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Not comparable
Dolly 2.0-12b: —, Llama 3-70B: 20.8 (#272)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| MMLU | 26.2% | 79.3% |
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multilingual Llama 3-70B leads
Dolly 2.0-12b: 17.4 (#291), Llama 3-70B: 33.8 (#246)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 836 | 1142 |
| LMArena Chinese | 836 | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
Dolly 2.0-12b: 38.9 (#299), Llama 3-70B: 62.8 (#233)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 814 | 1194 |
Long Context Not comparable
Dolly 2.0-12b: —, Llama 3-70B: 35.6 (#235)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |
Writing & Preference Llama 3-70B leads
Dolly 2.0-12b: 15.3 (#306), Llama 3-70B: 43.0 (#225)
| Benchmark | Dolly 2.0-12b | Llama 3-70B |
|---|---|---|
| LMArena Text | 851 | 1221 |
| LMArena Creative Writing | 864 | 1210 |
| LMArena Multi-Turn | 740 | 1223 |
Frequently asked questions
Is Dolly 2.0-12b better than Llama 3-70B?
Llama 3-70B is the stronger model overall, scoring 28.5 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.3 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Llama 3-70B share?
12 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Llama 3-70B has 31.