Model comparison
Dolly 2.0-12b vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 24.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Databricks
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 15.3.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Dolly 2.0-12b | Sonar | |
|---|---|---|
| Provider | Databricks | Perplexity |
| Noometry Index | 24.9 | 37.8 |
| Released | 2023-04-11 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 17 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Dolly 2.0-12b: 23.0 (#327), Sonar: 35.1 (#217)
| Benchmark | Dolly 2.0-12b | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 776 | — |
Reasoning Sonar leads
Dolly 2.0-12b: 14.6 (#315), Sonar: 20.3 (#221)
| Benchmark | Dolly 2.0-12b | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 804 | — |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 88.94 | — |
| HellaSwag | 70.8% | — |
| LiveBench | — | 46.9% |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Sonar leads
Dolly 2.0-12b: 25.0 (#250), Sonar: 31.3 (#197)
| Benchmark | Dolly 2.0-12b | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 871 | — |
Knowledge Not comparable
Dolly 2.0-12b: —, Sonar: —
| Benchmark | Dolly 2.0-12b | Sonar |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Not comparable
Dolly 2.0-12b: 17.4 (#291), Sonar: —
| Benchmark | Dolly 2.0-12b | Sonar |
|---|---|---|
| LMArena Non-English | 836 | — |
| LMArena Chinese | 836 | — |
Instruction Following Sonar leads
Dolly 2.0-12b: 38.9 (#299), Sonar: 71.5 (#146)
| Benchmark | Dolly 2.0-12b | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 814 | — |
Writing & Preference Sonar leads
Dolly 2.0-12b: 15.3 (#306), Sonar: 52.6 (#166)
| Benchmark | Dolly 2.0-12b | Sonar |
|---|---|---|
| LMArena Text | 851 | — |
| LMArena Creative Writing | 864 | — |
| LMArena Multi-Turn | 740 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Dolly 2.0-12b better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.1 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Sonar share?
0 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Sonar has 7.