Model comparison
Dolly 2.0-12b vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 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 Qwen3 32B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 15.2.
Side by side
| Dolly 2.0-12b | Qwen3 32B | |
|---|---|---|
| Provider | Databricks | Alibaba (Qwen) |
| Noometry Index | 25.5 | 39.2 |
| Released | 2023-04-11 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 17 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Dolly 2.0-12b: 23.4 (#332), Qwen3 32B: 37.7 (#190)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| LMArena Coding | 776 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Qwen3 32B leads
Dolly 2.0-12b: 15.3 (#316), Qwen3 32B: 20.2 (#241)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1334 |
| Epoch Capabilities Index | 89.67 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Qwen3 32B leads
Dolly 2.0-12b: 27.3 (#251), Qwen3 32B: 39.7 (#99)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| LMArena Math | 871 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
Knowledge Not comparable
Dolly 2.0-12b: —, Qwen3 32B: 40.0 (#125)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Qwen3 32B leads
Dolly 2.0-12b: 17.4 (#296), Qwen3 32B: 45.6 (#167)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 836 | 1317 |
| LMArena Chinese | 836 | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Qwen3 32B leads
Dolly 2.0-12b: 38.7 (#304), Qwen3 32B: 68.9 (#179)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 814 | 1305 |
Long Context Not comparable
Dolly 2.0-12b: —, Qwen3 32B: 43.8 (#87)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |
Writing & Preference Qwen3 32B leads
Dolly 2.0-12b: 15.2 (#311), Qwen3 32B: 52.9 (#163)
| Benchmark | Dolly 2.0-12b | Qwen3 32B |
|---|---|---|
| LMArena Text | 851 | 1340 |
| LMArena Creative Writing | 864 | 1297 |
| LMArena Multi-Turn | 740 | 1331 |
Frequently asked questions
Is Dolly 2.0-12b better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Qwen3 32B share?
10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Qwen3 32B has 26.