Model comparison
Dolly 2.0-12b vs Phi 3 Mini 4k Instruct
Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 25.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
Databricks
MicrosoftSummary
- They share 14 benchmarks with published results for both. Dolly 2.0-12b scores higher in 2 categories and Phi 3 Mini 4k Instruct in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi 3 Mini 4k Instruct leads 27.6 to 15.2.
Side by side
| Dolly 2.0-12b | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 25.5 | 27.9 |
| Released | 2023-04-11 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Mini 4k Instruct leads
Dolly 2.0-12b: 23.4 (#332), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 776 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Dolly 2.0-12b leads
Dolly 2.0-12b: 15.3 (#316), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 804 | 1072 |
| HellaSwag | 70.8% | 76.7% |
| WinoGrande | 61.8% | 70.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 89.67 | — |
| LiveBench | — | 22.4% |
| PIQA | 75.4% | — |
Math Too close to call
Dolly 2.0-12b: 27.3 (#251), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 871 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Not comparable
Dolly 2.0-12b: —, Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 84.9% |
| MMLU | 26.2% | 68.8% |
| OpenBookQA | 39.2% | 88% |
| LMArena Expert | — | 1045 |
| BoolQ | 56.3% | — |
| TriviaQA | — | 64% |
Multilingual Phi 3 Mini 4k Instruct leads
Dolly 2.0-12b: 17.4 (#296), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 836 | 1021 |
| LMArena Chinese | 836 | 1021 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1085 |
Instruction Following Phi 3 Mini 4k Instruct leads
Dolly 2.0-12b: 38.7 (#304), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 814 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Not comparable
Dolly 2.0-12b: —, Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |
Writing & Preference Phi 3 Mini 4k Instruct leads
Dolly 2.0-12b: 15.2 (#311), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Dolly 2.0-12b | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 851 | 1073 |
| LMArena Creative Writing | 864 | 1037 |
| LMArena Multi-Turn | 740 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Dolly 2.0-12b better than Phi 3 Mini 4k Instruct?
Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Phi 3 Mini 4k Instruct better for coding?
Phi 3 Mini 4k Instruct scores higher on coding benchmarks: 26.6 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Phi 3 Mini 4k Instruct share?
14 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.