Model comparison
Claude 2 vs Dolly 2.0-12b
Claude 2 and Dolly 2.0-12b score almost the same on the Noometry Index (25.0 vs 25.5), so choose on price, context window or the category you care about most.
Last verified . 2 shared benchmarks.
DatabricksSummary
- They share 2 benchmarks with published results for both. Claude 2 scores higher in 1 category and Dolly 2.0-12b in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Dolly 2.0-12b leads 27.3 to 9.3.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Dolly 2.0-12b | |
|---|---|---|
| Provider | Anthropic | Databricks |
| Noometry Index | 25.0 | 25.5 |
| Released | 2023-07-11 | 2023-04-11 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Dolly 2.0-12b: 23.4 (#332)
| Benchmark | Claude 2 | Dolly 2.0-12b |
|---|---|---|
| LMArena Coding | — | 776 |
| HumanEval+ | 61.6% | — |
Reasoning Claude 2 leads
Claude 2: 21.7 (#216), Dolly 2.0-12b: 15.3 (#316)
| Benchmark | Claude 2 | Dolly 2.0-12b |
|---|---|---|
| Epoch Capabilities Index | 120.13 | 89.67 |
| LMArena Hard Prompts | — | 804 |
| DTBench | 51.9% | — |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |
Math Dolly 2.0-12b leads
Claude 2: 9.3 (#320), Dolly 2.0-12b: 27.3 (#251)
| Benchmark | Claude 2 | Dolly 2.0-12b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 871 |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
Claude 2: 16.9 (#287), Dolly 2.0-12b: —
| Benchmark | Claude 2 | Dolly 2.0-12b |
|---|---|---|
| MMLU | 78.5% | 26.2% |
| GPQA Diamond | 34.7% | — |
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| OpenBookQA | — | 39.2% |
| TriviaQA | 87.5% | — |
Multilingual Not comparable
Claude 2: —, Dolly 2.0-12b: 17.4 (#296)
| Benchmark | Claude 2 | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | — | 836 |
| LMArena Chinese | — | 836 |
Instruction Following Not comparable
Claude 2: —, Dolly 2.0-12b: 38.7 (#304)
| Benchmark | Claude 2 | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | — | 814 |
Writing & Preference Not comparable
Claude 2: —, Dolly 2.0-12b: 15.2 (#311)
| Benchmark | Claude 2 | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | — | 851 |
| LMArena Creative Writing | — | 864 |
| LMArena Multi-Turn | — | 740 |
Frequently asked questions
Is Claude 2 better than Dolly 2.0-12b?
Claude 2 and Dolly 2.0-12b score almost the same on the Noometry Index (25.0 vs 25.5), so choose on price, context window or the category you care about most.
How many benchmarks do Claude 2 and Dolly 2.0-12b share?
2 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Dolly 2.0-12b has 17.