Model comparison
Dolly 2.0-12b vs Phi-4
Phi-4 is the stronger model overall, scoring 31.2 to 25.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
Databricks
MicrosoftSummary
- They share 11 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and Phi-4 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi-4 leads 40.5 to 15.2.
Side by side
| Dolly 2.0-12b | Phi-4 | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 25.5 | 31.2 |
| Released | 2023-04-11 | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.07 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 17 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Dolly 2.0-12b: 23.4 (#332), Phi-4: 34.4 (#239)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| LMArena Coding | 776 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Phi-4: 22.8 (#128)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Phi-4 leads
Dolly 2.0-12b: 15.3 (#316), Phi-4: 17.7 (#291)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1220 |
| Epoch Capabilities Index | 89.67 | 130.42 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| HellaSwag | 70.8% | — |
| LiveBench | — | 41.6% |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), Phi-4: 20.8 (#285)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| LMArena Math | 871 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Not comparable
Dolly 2.0-12b: —, Phi-4: 32.6 (#209)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| MMLU | 26.2% | 84.8% |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| LMArena Expert | — | 1203 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multilingual Phi-4 leads
Dolly 2.0-12b: 17.4 (#296), Phi-4: 37.2 (#237)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| LMArena Non-English | 836 | 1197 |
| LMArena Chinese | 836 | 1212 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Russian | — | 1209 |
| LMArena Spanish | — | 1234 |
Instruction Following Phi-4 leads
Dolly 2.0-12b: 38.7 (#304), Phi-4: 60.4 (#251)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 814 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Not comparable
Dolly 2.0-12b: —, Phi-4: 36.9 (#226)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| LMArena Longer Query | — | 1217 |
Writing & Preference Phi-4 leads
Dolly 2.0-12b: 15.2 (#311), Phi-4: 40.5 (#244)
| Benchmark | Dolly 2.0-12b | Phi-4 |
|---|---|---|
| LMArena Text | 851 | 1217 |
| LMArena Creative Writing | 864 | 1182 |
| LMArena Multi-Turn | 740 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Dolly 2.0-12b better than Phi-4?
Phi-4 is the stronger model overall, scoring 31.2 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Phi-4 better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Phi-4 share?
11 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Phi-4 has 37.