# DeepSeek LLM 67B vs Dolly 2.0-12b

> DeepSeek LLM 67B and Dolly 2.0-12b score almost the same on the Noometry Index (24.9 vs 25.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-dolly-2-0-12b
- Last updated: 2026-10-12
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 5 categories and Dolly 2.0-12b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Dolly 2.0-12b leads 27.3 to 8.7.

## Snapshot

| | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| Provider | DeepSeek | Databricks |
| Noometry Index | 24.9 | 25.5 |
| Rank | 347 | 342 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Dolly 2.0-12b: 23.4 (#332)

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| LMArena Coding | 1096 | 776 |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Dolly 2.0-12b: 15.3 (#316)

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| LMArena Hard Prompts | 1070 | 804 |
| Epoch Capabilities Index | 110.5 | 89.67 |
| Chess Puzzles | 0% | — |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Dolly 2.0-12b: 27.3 (#251)

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | 1108 | 871 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Dolly 2.0-12b: —

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| MMLU | — | 26.2% |
| OpenBookQA | — | 39.2% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Dolly 2.0-12b: 17.4 (#296)

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | 1073 | 836 |
| LMArena Chinese | 1132 | 836 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Dolly 2.0-12b: 38.7 (#304)

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | 1079 | 814 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Dolly 2.0-12b: —

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| LMArena Longer Query | 1092 | — |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Dolly 2.0-12b: 15.2 (#311)

| Benchmark | DeepSeek LLM 67B | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | 1105 | 851 |
| LMArena Creative Writing | 1067 | 864 |
| LMArena Multi-Turn | 1082 | 740 |

## FAQ

### Is DeepSeek LLM 67B better than Dolly 2.0-12b?

DeepSeek LLM 67B and Dolly 2.0-12b score almost the same on the Noometry Index (24.9 vs 25.5), so choose on price, context window or the category you care about most.

### Is DeepSeek LLM 67B or Dolly 2.0-12b better for coding?

DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 23.4 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Dolly 2.0-12b share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Dolly 2.0-12b has 17.