Model comparison
DeepSeek-V3.2-Speciale vs Dolly 2.0-12b
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 24.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
DatabricksSummary
- The widest gap is in writing & preference, where DeepSeek-V3.2-Speciale leads 46.1 to 15.3.
Side by side
| DeepSeek-V3.2-Speciale | Dolly 2.0-12b | |
|---|---|---|
| Provider | DeepSeek | Databricks |
| Noometry Index | 39.1 | 24.9 |
| Released | 2025-12-01 | 2023-04-11 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.58 | — |
| Output $ / M tokens | $1.68 | — |
| Results tracked | 3 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 39.9 (#136), Dolly 2.0-12b: 23.0 (#327)
| Benchmark | DeepSeek-V3.2-Speciale | Dolly 2.0-12b |
|---|---|---|
| WeirdML | 46.7% | — |
| LMArena Coding | — | 776 |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.1 (#65), Dolly 2.0-12b: 14.6 (#315)
| Benchmark | DeepSeek-V3.2-Speciale | Dolly 2.0-12b |
|---|---|---|
| SimpleBench | 52.6% | — |
| LMArena Hard Prompts | — | 804 |
| Epoch Capabilities Index | — | 88.94 |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Dolly 2.0-12b: 25.0 (#250)
| Benchmark | DeepSeek-V3.2-Speciale | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | — | 871 |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Dolly 2.0-12b: —
| Benchmark | DeepSeek-V3.2-Speciale | Dolly 2.0-12b |
|---|---|---|
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| MMLU | — | 26.2% |
| OpenBookQA | — | 39.2% |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, Dolly 2.0-12b: 17.4 (#291)
| Benchmark | DeepSeek-V3.2-Speciale | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | — | 836 |
| LMArena Chinese | — | 836 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, Dolly 2.0-12b: 38.9 (#299)
| Benchmark | DeepSeek-V3.2-Speciale | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | — | 814 |
Writing & Preference DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 46.1 (#217), Dolly 2.0-12b: 15.3 (#306)
| Benchmark | DeepSeek-V3.2-Speciale | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | — | 851 |
| LMArena Creative Writing | — | 864 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 740 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Dolly 2.0-12b?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 24.9 on the Noometry Index.
Is DeepSeek-V3.2-Speciale or Dolly 2.0-12b better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 23.0 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Speciale and Dolly 2.0-12b share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Dolly 2.0-12b has 17.