Model comparison
DeepSeek Coder 33B vs Dolly 2.0-12b
Dolly 2.0-12b has enough public results to be ranked (#339); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
DeepSeek
DatabricksSummary
- They share 4 benchmarks with published results for both. DeepSeek Coder 33B scores higher in 1 category and Dolly 2.0-12b in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 37.4 to 23.0.
Side by side
| DeepSeek Coder 33B | Dolly 2.0-12b | |
|---|---|---|
| Provider | DeepSeek | Databricks |
| Noometry Index | 38.3 | 24.9 |
| Released | 2023-11-02 | 2023-04-11 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 33B leads
DeepSeek Coder 33B: 37.4 (#180), Dolly 2.0-12b: 23.0 (#327)
| Benchmark | DeepSeek Coder 33B | Dolly 2.0-12b |
|---|---|---|
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 776 |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Reasoning Not comparable
DeepSeek Coder 33B: —, Dolly 2.0-12b: 14.6 (#315)
| Benchmark | DeepSeek Coder 33B | Dolly 2.0-12b |
|---|---|---|
| Epoch Capabilities Index | 95.74 | 88.94 |
| WinoGrande | 62% | 61.8% |
| LMArena Hard Prompts | — | 804 |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
Math Not comparable
DeepSeek Coder 33B: —, Dolly 2.0-12b: 25.0 (#250)
| Benchmark | DeepSeek Coder 33B | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | — | 871 |
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, Dolly 2.0-12b: —
| Benchmark | DeepSeek Coder 33B | Dolly 2.0-12b |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | 39.6% |
| MMLU | 39.4% | 26.2% |
| BoolQ | — | 56.3% |
| OpenBookQA | — | 39.2% |
Multilingual Not comparable
DeepSeek Coder 33B: —, Dolly 2.0-12b: 17.4 (#291)
| Benchmark | DeepSeek Coder 33B | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | — | 836 |
| LMArena Chinese | — | 836 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Dolly 2.0-12b: 38.9 (#299)
| Benchmark | DeepSeek Coder 33B | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | — | 814 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Dolly 2.0-12b: 15.3 (#306)
| Benchmark | DeepSeek Coder 33B | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | — | 851 |
| LMArena Creative Writing | — | 864 |
| LMArena Multi-Turn | — | 740 |
Frequently asked questions
Is DeepSeek Coder 33B better than Dolly 2.0-12b?
Dolly 2.0-12b has enough public results to be ranked (#339); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Dolly 2.0-12b better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 37.4 versus 23.0 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Dolly 2.0-12b share?
4 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Dolly 2.0-12b has 17.