Model comparison
Dolly 2.0-12b vs Llama 3.1-70B
Llama 3.1-70B is the stronger model overall, scoring 29.4 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Databricks
MetaSummary
- They share 11 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and Llama 3.1-70B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.1-70B leads 65.5 to 38.9.
Side by side
| Dolly 2.0-12b | Llama 3.1-70B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 24.9 | 29.4 |
| Released | 2023-04-11 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 17 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-70B leads
Dolly 2.0-12b: 23.0 (#327), Llama 3.1-70B: 29.8 (#292)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 776 | 1260 |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Llama 3.1-70B: 24.9 (#104)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
Reasoning Llama 3.1-70B leads
Dolly 2.0-12b: 14.6 (#315), Llama 3.1-70B: 20.8 (#215)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1241 |
| Epoch Capabilities Index | 88.94 | 125.91 |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 25.0 (#250), Llama 3.1-70B: 12.7 (#298)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 871 | 1252 |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |
Knowledge Not comparable
Dolly 2.0-12b: —, Llama 3.1-70B: 24.1 (#264)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| MMLU | 26.2% | 80.1% |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1209 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multilingual Llama 3.1-70B leads
Dolly 2.0-12b: 17.4 (#291), Llama 3.1-70B: 38.9 (#220)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 836 | 1219 |
| LMArena Chinese | 836 | 1215 |
| LMArena French | — | 1260 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1132 |
| LMArena Korean | — | 1140 |
| LMArena Russian | — | 1234 |
| LMArena Spanish | — | 1253 |
Instruction Following Llama 3.1-70B leads
Dolly 2.0-12b: 38.9 (#299), Llama 3.1-70B: 65.5 (#218)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 814 | 1231 |
| IFEval | — | 82.1% |
Long Context Not comparable
Dolly 2.0-12b: —, Llama 3.1-70B: 37.6 (#208)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | — | 1241 |
Writing & Preference Llama 3.1-70B leads
Dolly 2.0-12b: 15.3 (#306), Llama 3.1-70B: 35.6 (#262)
| Benchmark | Dolly 2.0-12b | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 851 | 1261 |
| LMArena Creative Writing | 864 | 1232 |
| LMArena Multi-Turn | 740 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
Frequently asked questions
Is Dolly 2.0-12b better than Llama 3.1-70B?
Llama 3.1-70B is the stronger model overall, scoring 29.4 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Llama 3.1-70B better for coding?
Llama 3.1-70B scores higher on coding benchmarks: 29.8 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Llama 3.1-70B share?
11 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Llama 3.1-70B has 35.