Model comparison
Dolly 2.0-12b vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 29.5 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Qwen2-72B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 41.0 to 15.3.
Side by side
| Dolly 2.0-12b | Qwen2-72B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 24.9 | 29.5 |
| Released | 2023-04-11 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Dolly 2.0-12b: 23.0 (#327), Qwen2-72B: 28.7 (#303)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| LMArena Coding | 776 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Dolly 2.0-12b: 14.6 (#315), Qwen2-72B: 22.2 (#184)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1191 |
| Epoch Capabilities Index | 88.94 | 125.27 |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Qwen2-72B leads
Dolly 2.0-12b: 25.0 (#250), Qwen2-72B: 27.9 (#232)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| LMArena Math | 871 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Not comparable
Dolly 2.0-12b: —, Qwen2-72B: 21.2 (#270)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| MMLU | 26.2% | 82.4% |
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multilingual Qwen2-72B leads
Dolly 2.0-12b: 17.4 (#291), Qwen2-72B: 36.0 (#239)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 836 | 1176 |
| LMArena Chinese | 836 | 1240 |
| LMArena French | — | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1168 |
Instruction Following Qwen2-72B leads
Dolly 2.0-12b: 38.9 (#299), Qwen2-72B: 62.0 (#236)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 814 | 1181 |
Long Context Not comparable
Dolly 2.0-12b: —, Qwen2-72B: 36.1 (#230)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1193 |
Writing & Preference Qwen2-72B leads
Dolly 2.0-12b: 15.3 (#306), Qwen2-72B: 41.0 (#236)
| Benchmark | Dolly 2.0-12b | Qwen2-72B |
|---|---|---|
| LMArena Text | 851 | 1203 |
| LMArena Creative Writing | 864 | 1181 |
| LMArena Multi-Turn | 740 | 1195 |
Frequently asked questions
Is Dolly 2.0-12b better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 29.5 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Qwen2-72B better for coding?
Qwen2-72B scores higher on coding benchmarks: 28.7 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Qwen2-72B share?
11 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Qwen2-72B has 26.