Model comparison
Dolly 2.0-12b vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 31.4 to 25.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Qwen-14B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Qwen-14B leads 52.4 to 38.7.
Side by side
| Dolly 2.0-12b | Qwen-14B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 25.5 | 31.4 |
| Released | 2023-04-11 | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Dolly 2.0-12b: 23.4 (#332), Qwen-14B: 31.2 (#288)
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| LMArena Coding | 776 | 1071 |
Reasoning Qwen-14B leads
Dolly 2.0-12b: 15.3 (#316), Qwen-14B: 19.6 (#257)
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1027 |
| Epoch Capabilities Index | 89.67 | 113.03 |
| PIQA | 75.4% | 79.9% |
| BIG-Bench Hard | — | 55% |
| HellaSwag | 70.8% | — |
| LAMBADA | — | 71.1% |
| WinoGrande | 61.8% | — |
Math Qwen-14B leads
Dolly 2.0-12b: 27.3 (#251), Qwen-14B: 31.2 (#227)
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| LMArena Math | 871 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Dolly 2.0-12b: —, Qwen-14B: —
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 84.4% |
| BoolQ | 56.3% | 86.2% |
| MMLU | 26.2% | 66.3% |
| OpenBookQA | 39.2% | — |
Multilingual Qwen-14B leads
Dolly 2.0-12b: 17.4 (#296), Qwen-14B: 27.5 (#275)
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| LMArena Non-English | 836 | 1041 |
| LMArena Chinese | 836 | 1077 |
Instruction Following Qwen-14B leads
Dolly 2.0-12b: 38.7 (#304), Qwen-14B: 52.4 (#289)
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 814 | 1031 |
Long Context Not comparable
Dolly 2.0-12b: —, Qwen-14B: 31.3 (#280)
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |
Writing & Preference Qwen-14B leads
Dolly 2.0-12b: 15.2 (#311), Qwen-14B: 27.6 (#299)
| Benchmark | Dolly 2.0-12b | Qwen-14B |
|---|---|---|
| LMArena Text | 851 | 1051 |
| LMArena Creative Writing | 864 | 1028 |
| LMArena Multi-Turn | 740 | 1022 |
Frequently asked questions
Is Dolly 2.0-12b better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 31.4 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Qwen-14B share?
14 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Qwen-14B has 18.