Model comparison
Dolly 2.0-12b vs Phi-3.5-mini
Dolly 2.0-12b has enough public results to be ranked (#342); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Databricks
MicrosoftSummary
- They share 2 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Phi-3.5-mini in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Phi-3.5-mini leads 34.6 to 23.4.
Side by side
| Dolly 2.0-12b | Phi-3.5-mini | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 25.5 | 36.9 |
| Released | 2023-04-11 | 2024-08-16 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-3.5-mini leads
Dolly 2.0-12b: 23.4 (#332), Phi-3.5-mini: 34.6 (#232)
| Benchmark | Dolly 2.0-12b | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 776 | — |
| BigCodeBench Complete | — | 38.5% |
Reasoning Not comparable
Dolly 2.0-12b: 15.3 (#316), Phi-3.5-mini: —
| Benchmark | Dolly 2.0-12b | Phi-3.5-mini |
|---|---|---|
| PIQA | 75.4% | 81% |
| LMArena Hard Prompts | 804 | — |
| Epoch Capabilities Index | 89.67 | — |
| HellaSwag | 70.8% | — |
| WinoGrande | 61.8% | — |
Math Not comparable
Dolly 2.0-12b: 27.3 (#251), Phi-3.5-mini: —
| Benchmark | Dolly 2.0-12b | Phi-3.5-mini |
|---|---|---|
| LMArena Math | 871 | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Dolly 2.0-12b: —, Phi-3.5-mini: —
| Benchmark | Dolly 2.0-12b | Phi-3.5-mini |
|---|---|---|
| BoolQ | 56.3% | 78% |
| ARC (AI2) Challenge | 39.6% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Not comparable
Dolly 2.0-12b: 17.4 (#296), Phi-3.5-mini: —
| Benchmark | Dolly 2.0-12b | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 836 | — |
| LMArena Chinese | 836 | — |
Instruction Following Not comparable
Dolly 2.0-12b: 38.7 (#304), Phi-3.5-mini: —
| Benchmark | Dolly 2.0-12b | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 814 | — |
Writing & Preference Not comparable
Dolly 2.0-12b: 15.2 (#311), Phi-3.5-mini: —
| Benchmark | Dolly 2.0-12b | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 851 | — |
| LMArena Creative Writing | 864 | — |
| LMArena Multi-Turn | 740 | — |
Frequently asked questions
Is Dolly 2.0-12b better than Phi-3.5-mini?
Dolly 2.0-12b has enough public results to be ranked (#342); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Dolly 2.0-12b or Phi-3.5-mini better for coding?
Phi-3.5-mini scores higher on coding benchmarks: 34.6 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Phi-3.5-mini share?
2 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Phi-3.5-mini has 5.