# Dolly 2.0-12b vs GPT-6 Sol

> GPT-6 Sol is the stronger model overall, scoring 49.2 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dolly-2-0-12b-vs-gpt-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and GPT-6 Sol in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-6 Sol leads 72.3 to 15.3.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.

## Snapshot

| | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 24.9 | 49.2 |
| Rank | 339 | 46 |
| Context | — | 1.05M |
| Input $/M | — | $2 |
| Output $/M | — | $10 |
| Weights | Open | Proprietary |

## Coding

- Dolly 2.0-12b: 23.0 (#327)
- GPT-6 Sol: 59.6 (#11)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 776 | 1453 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| LMArena WebDev | — | 1692 |

## Agentic & Tool Use

- Dolly 2.0-12b: —
- GPT-6 Sol: 33.5 (#49)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| GDP.pdf | — | 28% |

## Reasoning

- Dolly 2.0-12b: 14.6 (#315)
- GPT-6 Sol: 49.3 (#34)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 804 | 1420 |
| NYT Connections (extended) | — | 90.1% |
| EBR-Bench | — | 53.3% |
| Epoch Capabilities Index | 88.94 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |

## Math

- Dolly 2.0-12b: 25.0 (#250)
- GPT-6 Sol: 35.8 (#135)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Math | 871 | 1404 |

## Knowledge

- Dolly 2.0-12b: —
- GPT-6 Sol: 43.0 (#87)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | — | 6.5% |
| LMArena Expert | — | 1449 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |

## Multimodal

- Dolly 2.0-12b: —
- GPT-6 Sol: 47.6 (#9)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| Furniture Assembly | — | 58.3% |

## Multilingual

- Dolly 2.0-12b: 17.4 (#291)
- GPT-6 Sol: 51.0 (#113)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 836 | 1389 |
| LMArena Chinese | 836 | 1416 |
| LMArena Russian | — | 1407 |
| LMArena Spanish | — | 1377 |

## Instruction Following

- Dolly 2.0-12b: 38.9 (#299)
- GPT-6 Sol: 74.4 (#97)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 814 | 1406 |

## Long Context

- Dolly 2.0-12b: —
- GPT-6 Sol: 43.2 (#100)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | — | 1415 |

## Writing & Preference

- Dolly 2.0-12b: 15.3 (#306)
- GPT-6 Sol: 72.3 (#15)

| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Text | 851 | 1396 |
| LMArena Creative Writing | 864 | 1392 |
| LMArena Multi-Turn | 740 | 1405 |
| EQ-Bench Creative Writing | — | 2125 |

## FAQ

### Is Dolly 2.0-12b better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 49.2 to 24.9 on the Noometry Index.

### Is Dolly 2.0-12b or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 23.0 in the Noometry coding category.

### How many benchmarks do Dolly 2.0-12b and GPT-6 Sol share?

9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and GPT-6 Sol has 22.