Model comparison
Dolly 2.0-12b vs Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
Databricks
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and Qwen2.5 72B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.7 to 15.2.
Side by side
| Dolly 2.0-12b | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 25.5 | 31.9 |
| Released | 2023-04-11 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 17 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Dolly 2.0-12b: 23.4 (#332), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 776 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Dolly 2.0-12b: 15.3 (#316), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 804 | 1271 |
| Epoch Capabilities Index | 89.67 | 129 |
| HellaSwag | 70.8% | 84.8% |
| PIQA | 75.4% | 82.6% |
| WinoGrande | 61.8% | 82.3% |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 871 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Not comparable
Dolly 2.0-12b: —, Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 94.5% |
| MMLU | 26.2% | 85.3% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
| TriviaQA | — | 71.9% |
Multilingual Qwen2.5 72B Instruct leads
Dolly 2.0-12b: 17.4 (#296), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 836 | 1252 |
| LMArena Chinese | 836 | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Dolly 2.0-12b: 38.7 (#304), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 814 | 1254 |
| IFEval | — | 80.6% |
Long Context Not comparable
Dolly 2.0-12b: —, Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Dolly 2.0-12b: 15.2 (#311), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Dolly 2.0-12b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 851 | 1269 |
| LMArena Creative Writing | 864 | 1221 |
| LMArena Multi-Turn | 740 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Dolly 2.0-12b better than Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Qwen2.5 72B Instruct share?
15 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Qwen2.5 72B Instruct has 43.