Model comparison
Codellama 70b Instruct vs Dolly 2.0-12b
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 24.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
DatabricksSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 5 categories and Dolly 2.0-12b in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Codellama 70b Instruct leads 33.6 to 15.3.
Side by side
| Codellama 70b Instruct | Dolly 2.0-12b | |
|---|---|---|
| Provider | Meta | Databricks |
| Noometry Index | 33.3 | 24.9 |
| Released | — | 2023-04-11 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.0 (#189), Dolly 2.0-12b: 23.0 (#327)
| Benchmark | Codellama 70b Instruct | Dolly 2.0-12b |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 776 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 19.2 (#241), Dolly 2.0-12b: 14.6 (#315)
| Benchmark | Codellama 70b Instruct | Dolly 2.0-12b |
|---|---|---|
| LMArena Hard Prompts | 1052 | 804 |
| Epoch Capabilities Index | — | 88.94 |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |
Math Not comparable
Codellama 70b Instruct: —, Dolly 2.0-12b: 25.0 (#250)
| Benchmark | Codellama 70b Instruct | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | — | 871 |
Knowledge Not comparable
Codellama 70b Instruct: —, Dolly 2.0-12b: —
| Benchmark | Codellama 70b Instruct | Dolly 2.0-12b |
|---|---|---|
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| MMLU | — | 26.2% |
| OpenBookQA | — | 39.2% |
Multilingual Codellama 70b Instruct leads
Codellama 70b Instruct: 24.9 (#283), Dolly 2.0-12b: 17.4 (#291)
| Benchmark | Codellama 70b Instruct | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | 992 | 836 |
| LMArena Chinese | — | 836 |
Instruction Following Codellama 70b Instruct leads
Codellama 70b Instruct: 52.1 (#288), Dolly 2.0-12b: 38.9 (#299)
| Benchmark | Codellama 70b Instruct | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | 1024 | 814 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.6 (#272), Dolly 2.0-12b: 15.3 (#306)
| Benchmark | Codellama 70b Instruct | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | 1057 | 851 |
| LMArena Creative Writing | — | 864 |
| LMArena Multi-Turn | — | 740 |
Frequently asked questions
Is Codellama 70b Instruct better than Dolly 2.0-12b?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 24.9 on the Noometry Index.
Is Codellama 70b Instruct or Dolly 2.0-12b better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 23.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Dolly 2.0-12b share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Dolly 2.0-12b has 17.