Model comparison
DeepSeek-V2.5 (Sep 2024) vs Dolly 2.0-12b
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
DatabricksSummary
- They share 9 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 6 categories and Dolly 2.0-12b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 49.8 to 15.2.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b | |
|---|---|---|
| Provider | DeepSeek | Databricks |
| Noometry Index | 37.6 | 25.5 |
| Released | 2024-09-06 | 2023-04-11 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Dolly 2.0-12b: 23.4 (#332)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Coding | 1309 | 776 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Dolly 2.0-12b: 15.3 (#316)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Hard Prompts | 1289 | 804 |
| Epoch Capabilities Index | — | 89.67 |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Dolly 2.0-12b: 27.3 (#251)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | 1288 | 871 |
Knowledge Not comparable
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Dolly 2.0-12b: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Expert | 1266 | — |
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| MMLU | — | 26.2% |
| OpenBookQA | — | 39.2% |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Dolly 2.0-12b: 17.4 (#296)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | 1273 | 836 |
| LMArena Chinese | 1318 | 836 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Dolly 2.0-12b: 38.7 (#304)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | 1280 | 814 |
Long Context Not comparable
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Dolly 2.0-12b: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Longer Query | 1301 | — |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Dolly 2.0-12b: 15.2 (#311)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | 1294 | 851 |
| LMArena Creative Writing | 1285 | 864 |
| LMArena Multi-Turn | 1297 | 740 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Dolly 2.0-12b?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 25.5 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Dolly 2.0-12b better for coding?
DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.7 versus 23.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Dolly 2.0-12b share?
9 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Dolly 2.0-12b has 17.