Model comparison
Dolly 2.0-12b vs Phi-2
Dolly 2.0-12b has enough public results to be ranked (#342); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
Databricks
MicrosoftSummary
- They share 6 benchmarks with published results for both.
Side by side
| Dolly 2.0-12b | Phi-2 | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 25.5 | — |
| Released | 2023-04-11 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Dolly 2.0-12b: 23.4 (#332), Phi-2: —
| Benchmark | Dolly 2.0-12b | Phi-2 |
|---|---|---|
| LMArena Coding | 776 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Dolly 2.0-12b: 15.3 (#316), Phi-2: —
| Benchmark | Dolly 2.0-12b | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 89.67 | 107.94 |
| HellaSwag | 70.8% | 53.6% |
| WinoGrande | 61.8% | 54.7% |
| LMArena Hard Prompts | 804 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| PIQA | 75.4% | — |
Math Not comparable
Dolly 2.0-12b: 27.3 (#251), Phi-2: —
| Benchmark | Dolly 2.0-12b | Phi-2 |
|---|---|---|
| LMArena Math | 871 | — |
Knowledge Not comparable
Dolly 2.0-12b: —, Phi-2: —
| Benchmark | Dolly 2.0-12b | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 75.9% |
| MMLU | 26.2% | 58.4% |
| OpenBookQA | 39.2% | 73.6% |
| BoolQ | 56.3% | — |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Dolly 2.0-12b: 17.4 (#296), Phi-2: —
| Benchmark | Dolly 2.0-12b | Phi-2 |
|---|---|---|
| LMArena Non-English | 836 | — |
| LMArena Chinese | 836 | — |
Instruction Following Not comparable
Dolly 2.0-12b: 38.7 (#304), Phi-2: —
| Benchmark | Dolly 2.0-12b | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 814 | — |
Writing & Preference Not comparable
Dolly 2.0-12b: 15.2 (#311), Phi-2: —
| Benchmark | Dolly 2.0-12b | Phi-2 |
|---|---|---|
| LMArena Text | 851 | — |
| LMArena Creative Writing | 864 | — |
| LMArena Multi-Turn | 740 | — |
Frequently asked questions
Is Dolly 2.0-12b better than Phi-2?
Dolly 2.0-12b has enough public results to be ranked (#342); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Dolly 2.0-12b and Phi-2 share?
6 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Phi-2 has 11.