Model comparison
Dolly 2.0-12b vs Falcon-180B
Falcon-180B is the stronger model overall, scoring 32.2 to 25.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
Databricks
Technology Innovation InstituteSummary
- They share 14 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Falcon-180B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Falcon-180B leads 53.4 to 38.7.
Side by side
| Dolly 2.0-12b | Falcon-180B | |
|---|---|---|
| Provider | Databricks | Technology Innovation Institute |
| Noometry Index | 25.5 | 32.2 |
| Released | 2023-04-11 | 2023-09-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Dolly 2.0-12b: 23.4 (#332), Falcon-180B: —
| Benchmark | Dolly 2.0-12b | Falcon-180B |
|---|---|---|
| LMArena Coding | 776 | — |
Reasoning Falcon-180B leads
Dolly 2.0-12b: 15.3 (#316), Falcon-180B: 19.1 (#269)
| Benchmark | Dolly 2.0-12b | Falcon-180B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1007 |
| Epoch Capabilities Index | 89.67 | 112.13 |
| HellaSwag | 70.8% | 89% |
| PIQA | 75.4% | 84.9% |
| WinoGrande | 61.8% | 87.1% |
| LAMBADA | — | 79.8% |
Math Not comparable
Dolly 2.0-12b: 27.3 (#251), Falcon-180B: —
| Benchmark | Dolly 2.0-12b | Falcon-180B |
|---|---|---|
| LMArena Math | 871 | — |
| GSM8K | — | 54.4% |
Knowledge Not comparable
Dolly 2.0-12b: —, Falcon-180B: —
| Benchmark | Dolly 2.0-12b | Falcon-180B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 67.8% |
| BoolQ | 56.3% | 89% |
| MMLU | 26.2% | 70.6% |
| OpenBookQA | 39.2% | 64.2% |
Multilingual Falcon-180B leads
Dolly 2.0-12b: 17.4 (#296), Falcon-180B: 25.2 (#286)
| Benchmark | Dolly 2.0-12b | Falcon-180B |
|---|---|---|
| LMArena Non-English | 836 | 1000 |
| LMArena Chinese | 836 | — |
Instruction Following Falcon-180B leads
Dolly 2.0-12b: 38.7 (#304), Falcon-180B: 53.4 (#286)
| Benchmark | Dolly 2.0-12b | Falcon-180B |
|---|---|---|
| LMArena Instruction Following | 814 | 1047 |
Writing & Preference Falcon-180B leads
Dolly 2.0-12b: 15.2 (#311), Falcon-180B: 29.1 (#295)
| Benchmark | Dolly 2.0-12b | Falcon-180B |
|---|---|---|
| LMArena Text | 851 | 1054 |
| LMArena Creative Writing | 864 | 1089 |
| LMArena Multi-Turn | 740 | 1013 |
Frequently asked questions
Is Dolly 2.0-12b better than Falcon-180B?
Falcon-180B is the stronger model overall, scoring 32.2 to 25.5 on the Noometry Index.
How many benchmarks do Dolly 2.0-12b and Falcon-180B share?
14 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Falcon-180B has 16.