Model comparison
Dolly 2.0-12b vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 32.4 to 24.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
Databricks
MicrosoftSummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Wizardlm 70b in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Wizardlm 70b leads 34.9 to 15.3.
Side by side
| Dolly 2.0-12b | Wizardlm 70b | |
|---|---|---|
| Provider | Databricks | Microsoft |
| Noometry Index | 24.9 | 32.4 |
| Released | 2023-04-11 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 70b leads
Dolly 2.0-12b: 23.0 (#327), Wizardlm 70b: 30.9 (#280)
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 776 | 1081 |
Reasoning Wizardlm 70b leads
Dolly 2.0-12b: 14.6 (#315), Wizardlm 70b: 19.8 (#231)
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 804 | 1079 |
| Epoch Capabilities Index | 88.94 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Wizardlm 70b leads
Dolly 2.0-12b: 25.0 (#250), Wizardlm 70b: 29.7 (#216)
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| LMArena Math | 871 | 1116 |
Knowledge Not comparable
Dolly 2.0-12b: —, Wizardlm 70b: —
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Wizardlm 70b leads
Dolly 2.0-12b: 17.4 (#291), Wizardlm 70b: 29.8 (#260)
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 836 | 1078 |
| LMArena Chinese | 836 | 1052 |
| LMArena German | — | 1083 |
| LMArena Russian | — | 1155 |
Instruction Following Wizardlm 70b leads
Dolly 2.0-12b: 38.9 (#299), Wizardlm 70b: 56.5 (#268)
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 814 | 1093 |
Long Context Not comparable
Dolly 2.0-12b: —, Wizardlm 70b: 33.3 (#258)
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | — | 1097 |
Writing & Preference Wizardlm 70b leads
Dolly 2.0-12b: 15.3 (#306), Wizardlm 70b: 34.9 (#264)
| Benchmark | Dolly 2.0-12b | Wizardlm 70b |
|---|---|---|
| LMArena Text | 851 | 1120 |
| LMArena Creative Writing | 864 | 1149 |
| LMArena Multi-Turn | 740 | 1108 |
Frequently asked questions
Is Dolly 2.0-12b better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 32.4 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Wizardlm 70b better for coding?
Wizardlm 70b scores higher on coding benchmarks: 30.9 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Wizardlm 70b share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Wizardlm 70b has 12.