Model comparison
Dolly 2.0-12b vs Gemma 2B
Gemma 2B is the stronger model overall, scoring 29.6 to 25.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
Databricks
GoogleSummary
- They share 16 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Gemma 2B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 2B leads 48.5 to 38.7.
Side by side
| Dolly 2.0-12b | Gemma 2B | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 25.5 | 29.6 |
| Released | 2023-04-11 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2B leads
Dolly 2.0-12b: 23.4 (#332), Gemma 2B: 29.4 (#305)
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| LMArena Coding | 776 | 1010 |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning Gemma 2B leads
Dolly 2.0-12b: 15.3 (#316), Gemma 2B: 18.8 (#275)
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 804 | 989 |
| Epoch Capabilities Index | 89.67 | 94.2 |
| HellaSwag | 70.8% | 71.4% |
| PIQA | 75.4% | 77.3% |
| WinoGrande | 61.8% | 65.4% |
| BIG-Bench Hard | — | 35.2% |
Math Gemma 2B leads
Dolly 2.0-12b: 27.3 (#251), Gemma 2B: 30.0 (#239)
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| LMArena Math | 871 | 1009 |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Dolly 2.0-12b: —, Gemma 2B: —
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 42.1% |
| BoolQ | 56.3% | 69.4% |
| MMLU | 26.2% | 42.3% |
| OpenBookQA | 39.2% | — |
| TriviaQA | — | 53.2% |
Multilingual Gemma 2B leads
Dolly 2.0-12b: 17.4 (#296), Gemma 2B: 23.0 (#294)
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| LMArena Non-English | 836 | 958 |
| LMArena Chinese | 836 | 986 |
| LMArena Russian | — | 937 |
Instruction Following Gemma 2B leads
Dolly 2.0-12b: 38.7 (#304), Gemma 2B: 48.5 (#302)
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 814 | 970 |
Long Context Not comparable
Dolly 2.0-12b: —, Gemma 2B: 29.9 (#291)
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |
Writing & Preference Gemma 2B leads
Dolly 2.0-12b: 15.2 (#311), Gemma 2B: 24.0 (#308)
| Benchmark | Dolly 2.0-12b | Gemma 2B |
|---|---|---|
| LMArena Text | 851 | 1002 |
| LMArena Creative Writing | 864 | 987 |
| LMArena Multi-Turn | 740 | 945 |
Frequently asked questions
Is Dolly 2.0-12b better than Gemma 2B?
Gemma 2B is the stronger model overall, scoring 29.6 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Gemma 2B better for coding?
Gemma 2B scores higher on coding benchmarks: 29.4 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Gemma 2B share?
16 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Gemma 2B has 23.