Model comparison
Dolly 2.0-12b vs Granite 3.1 8b Instruct
Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 24.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
DatabricksSummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Granite 3.1 8b Instruct in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 3.1 8b Instruct leads 35.7 to 15.3.
Side by side
| Dolly 2.0-12b | Granite 3.1 8b Instruct | |
|---|---|---|
| Provider | Databricks | IBM |
| Noometry Index | 24.9 | 31.8 |
| Released | 2023-04-11 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 3.1 8b Instruct leads
Dolly 2.0-12b: 23.0 (#327), Granite 3.1 8b Instruct: 33.9 (#232)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Coding | 776 | 1186 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Granite 3.1 8b Instruct: 23.9 (#113)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Granite 3.1 8b Instruct leads
Dolly 2.0-12b: 14.6 (#315), Granite 3.1 8b Instruct: 21.2 (#204)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 804 | 1146 |
| Epoch Capabilities Index | 88.94 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Granite 3.1 8b Instruct leads
Dolly 2.0-12b: 25.0 (#250), Granite 3.1 8b Instruct: 30.4 (#210)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | 871 | 1152 |
Knowledge Not comparable
Dolly 2.0-12b: —, Granite 3.1 8b Instruct: 30.6 (#218)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | — | 1142 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Granite 3.1 8b Instruct leads
Dolly 2.0-12b: 17.4 (#291), Granite 3.1 8b Instruct: 31.1 (#255)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | 836 | 1099 |
| LMArena Chinese | 836 | 1145 |
| LMArena Russian | — | 1092 |
Instruction Following Granite 3.1 8b Instruct leads
Dolly 2.0-12b: 38.9 (#299), Granite 3.1 8b Instruct: 58.9 (#254)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 814 | 1131 |
Long Context Not comparable
Dolly 2.0-12b: —, Granite 3.1 8b Instruct: 35.2 (#236)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1162 |
Writing & Preference Granite 3.1 8b Instruct leads
Dolly 2.0-12b: 15.3 (#306), Granite 3.1 8b Instruct: 35.7 (#261)
| Benchmark | Dolly 2.0-12b | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | 851 | 1150 |
| LMArena Creative Writing | 864 | 1129 |
| LMArena Multi-Turn | 740 | 1108 |
Frequently asked questions
Is Dolly 2.0-12b better than Granite 3.1 8b Instruct?
Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Granite 3.1 8b Instruct better for coding?
Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Granite 3.1 8b Instruct share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Granite 3.1 8b Instruct has 13.