Model comparison
Dolly 2.0-12b vs Qwen1.5-7B
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 25.5 on the Noometry Index.
Last verified . 10 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Qwen1.5-7B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Qwen1.5-7B leads 54.1 to 38.7.
Side by side
| Dolly 2.0-12b | Qwen1.5-7B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 25.5 | 31.4 |
| Released | 2023-04-11 | 2024-02-04 |
| 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 Qwen1.5-7B leads
Dolly 2.0-12b: 23.4 (#332), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 776 | 1107 |
Reasoning Qwen1.5-7B leads
Dolly 2.0-12b: 15.3 (#316), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1065 |
| Epoch Capabilities Index | 89.67 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Qwen1.5-7B leads
Dolly 2.0-12b: 27.3 (#251), Qwen1.5-7B: 31.4 (#224)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 871 | 1080 |
Knowledge Not comparable
Dolly 2.0-12b: —, Qwen1.5-7B: 28.7 (#243)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| MMLU | 26.2% | 62.6% |
| LMArena Expert | — | 1055 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multilingual Qwen1.5-7B leads
Dolly 2.0-12b: 17.4 (#296), Qwen1.5-7B: 28.5 (#271)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 836 | 1058 |
| LMArena Chinese | 836 | 1141 |
| LMArena Russian | — | 1006 |
Instruction Following Qwen1.5-7B leads
Dolly 2.0-12b: 38.7 (#304), Qwen1.5-7B: 54.1 (#281)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 814 | 1058 |
Long Context Not comparable
Dolly 2.0-12b: —, Qwen1.5-7B: 33.1 (#266)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | — | 1090 |
Writing & Preference Qwen1.5-7B leads
Dolly 2.0-12b: 15.2 (#311), Qwen1.5-7B: 29.6 (#293)
| Benchmark | Dolly 2.0-12b | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 851 | 1083 |
| LMArena Creative Writing | 864 | 1035 |
| LMArena Multi-Turn | 740 | 1062 |
Frequently asked questions
Is Dolly 2.0-12b better than Qwen1.5-7B?
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Qwen1.5-7B better for coding?
Qwen1.5-7B scores higher on coding benchmarks: 32.2 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Qwen1.5-7B share?
10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Qwen1.5-7B has 13.