Model comparison
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.
Last verified . 9 shared benchmarks.
DatabricksSummary
- 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.
Side by side
| Dolly 2.0-12b | GPT-6 Sol | |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 24.9 | 49.2 |
| Released | 2023-04-11 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
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 Not comparable
Dolly 2.0-12b: —, GPT-6 Sol: 33.5 (#49)
| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| GDP.pdf | — | 28% |
Reasoning GPT-6 Sol leads
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 GPT-6 Sol leads
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 Not comparable
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 Not comparable
Dolly 2.0-12b: —, GPT-6 Sol: 47.6 (#9)
| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
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 GPT-6 Sol leads
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 Not comparable
Dolly 2.0-12b: —, GPT-6 Sol: 43.2 (#100)
| Benchmark | Dolly 2.0-12b | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | — | 1415 |
Writing & Preference GPT-6 Sol leads
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 |
Frequently asked questions
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.