Model comparison
Dolly 2.0-12b vs Gemma 7B
Gemma 7B is the stronger model overall, scoring 29.5 to 24.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
GoogleSummary
- They share 17 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Gemma 7B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 7B leads 51.7 to 38.9.
Side by side
| Dolly 2.0-12b | Gemma 7B | |
|---|---|---|
| Provider | Databricks | |
| Noometry Index | 24.9 | 29.5 |
| Released | 2023-04-11 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 7B leads
Dolly 2.0-12b: 23.0 (#327), Gemma 7B: 29.9 (#290)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| LMArena Coding | 776 | 1048 |
| HumanEval+ | — | 28.7% |
| MBPP+ | — | 43.4% |
Reasoning Gemma 7B leads
Dolly 2.0-12b: 14.6 (#315), Gemma 7B: 19.0 (#247)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1042 |
| Epoch Capabilities Index | 88.94 | 111.74 |
| HellaSwag | 70.8% | 82.2% |
| PIQA | 75.4% | 81.2% |
| WinoGrande | 61.8% | 79% |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
Math Gemma 7B leads
Dolly 2.0-12b: 25.0 (#250), Gemma 7B: 28.7 (#225)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| LMArena Math | 871 | 1066 |
| GSM8K | — | 46.4% |
Knowledge Not comparable
Dolly 2.0-12b: —, Gemma 7B: 26.8 (#248)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 78.3% |
| BoolQ | 56.3% | 83.2% |
| MMLU | 26.2% | 66.1% |
| OpenBookQA | 39.2% | 78.6% |
| LMArena Expert | — | 1002 |
| TriviaQA | — | 72.3% |
Multilingual Gemma 7B leads
Dolly 2.0-12b: 17.4 (#291), Gemma 7B: 25.3 (#282)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| LMArena Non-English | 836 | 999 |
| LMArena Chinese | 836 | 1035 |
| LMArena French | — | 1024 |
| LMArena Russian | — | 993 |
Instruction Following Gemma 7B leads
Dolly 2.0-12b: 38.9 (#299), Gemma 7B: 51.7 (#290)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 814 | 1017 |
Long Context Not comparable
Dolly 2.0-12b: —, Gemma 7B: 31.1 (#277)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| LMArena Longer Query | — | 1022 |
Writing & Preference Gemma 7B leads
Dolly 2.0-12b: 15.3 (#306), Gemma 7B: 27.2 (#297)
| Benchmark | Dolly 2.0-12b | Gemma 7B |
|---|---|---|
| LMArena Text | 851 | 1056 |
| LMArena Creative Writing | 864 | 1024 |
| LMArena Multi-Turn | 740 | 963 |
Frequently asked questions
Is Dolly 2.0-12b better than Gemma 7B?
Gemma 7B is the stronger model overall, scoring 29.5 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Gemma 7B better for coding?
Gemma 7B scores higher on coding benchmarks: 29.9 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Gemma 7B share?
17 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Gemma 7B has 27.