Model comparison
Dolly 2.0-12b vs StarCoder 2 3B
Dolly 2.0-12b has enough public results to be ranked (#339); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
Databricks
NVIDIASummary
- They share 4 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 3B leads 32.9 to 23.0.
Side by side
| Dolly 2.0-12b | StarCoder 2 3B | |
|---|---|---|
| Provider | Databricks | NVIDIA |
| Noometry Index | 24.9 | 35.8 |
| Released | 2023-04-11 | 2024-02-22 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 3B leads
Dolly 2.0-12b: 23.0 (#327), StarCoder 2 3B: 32.9
| Benchmark | Dolly 2.0-12b | StarCoder 2 3B |
|---|---|---|
| LMArena Coding | 776 | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
Dolly 2.0-12b: 14.6 (#315), StarCoder 2 3B: —
| Benchmark | Dolly 2.0-12b | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 88.94 | 88.01 |
| WinoGrande | 61.8% | 57.1% |
| LMArena Hard Prompts | 804 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
Math Not comparable
Dolly 2.0-12b: 25.0 (#250), StarCoder 2 3B: —
| Benchmark | Dolly 2.0-12b | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 871 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Dolly 2.0-12b: —, StarCoder 2 3B: —
| Benchmark | Dolly 2.0-12b | StarCoder 2 3B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 34.2% |
| MMLU | 26.2% | 36.6% |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multilingual Not comparable
Dolly 2.0-12b: 17.4 (#291), StarCoder 2 3B: —
| Benchmark | Dolly 2.0-12b | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 836 | — |
| LMArena Chinese | 836 | — |
Instruction Following Not comparable
Dolly 2.0-12b: 38.9 (#299), StarCoder 2 3B: —
| Benchmark | Dolly 2.0-12b | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 814 | — |
Writing & Preference Not comparable
Dolly 2.0-12b: 15.3 (#306), StarCoder 2 3B: —
| Benchmark | Dolly 2.0-12b | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 851 | — |
| LMArena Creative Writing | 864 | — |
| LMArena Multi-Turn | 740 | — |
Frequently asked questions
Is Dolly 2.0-12b better than StarCoder 2 3B?
Dolly 2.0-12b has enough public results to be ranked (#339); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Dolly 2.0-12b or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 32.9 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and StarCoder 2 3B share?
4 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and StarCoder 2 3B has 7.