Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Dolly 2.0-12b
Dolly 2.0-12b has enough public results to be ranked (#342); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
DeepSeek
DatabricksSummary
- They share 6 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) 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-V2 (MoE-236B, May 2024) leads 40.4 to 23.4.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b | |
|---|---|---|
| Provider | DeepSeek | Databricks |
| Noometry Index | 40.3 | 25.5 |
| Released | 2024-05-07 | 2023-04-11 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Dolly 2.0-12b: 23.4 (#332)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 776 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Dolly 2.0-12b: 15.3 (#316)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 89.67 |
| HellaSwag | 87.1% | 70.8% |
| PIQA | 83.9% | 75.4% |
| WinoGrande | 86.3% | 61.8% |
| LMArena Hard Prompts | — | 804 |
| BIG-Bench Hard | 78.8% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Dolly 2.0-12b: 27.3 (#251)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | — | 871 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Dolly 2.0-12b: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 39.6% |
| MMLU | 78.4% | 26.2% |
| BoolQ | — | 56.3% |
| OpenBookQA | — | 39.2% |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Dolly 2.0-12b: 17.4 (#296)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | — | 836 |
| LMArena Chinese | — | 836 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Dolly 2.0-12b: 38.7 (#304)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | — | 814 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Dolly 2.0-12b: 15.2 (#311)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | — | 851 |
| LMArena Creative Writing | — | 864 |
| LMArena Multi-Turn | — | 740 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Dolly 2.0-12b?
Dolly 2.0-12b has enough public results to be ranked (#342); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Dolly 2.0-12b better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 23.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Dolly 2.0-12b share?
6 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Dolly 2.0-12b has 17.