Model comparison
Dolly 2.0-12b vs GPT-4o
GPT-4o is the stronger model overall, scoring 28.6 to 25.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
DatabricksSummary
- They share 11 benchmarks with published results for both. Dolly 2.0-12b scores higher in 2 categories and GPT-4o in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4o leads 52.6 to 15.2.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Dolly 2.0-12b | GPT-4o | |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 25.5 | 28.6 |
| Released | 2023-04-11 | 2024-05-13 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $10 |
| Results tracked | 17 | 72 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4o leads
Dolly 2.0-12b: 23.4 (#332), GPT-4o: 24.8 (#328)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| LMArena Coding | 776 | 1297 |
| SWE-bench Verified | — | 31% |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| GSO | — | 0% |
| WeirdML | — | 25.1% |
| BigCodeBench Instruct | — | 51.1% |
| LiveBench Coding | — | 51.4% |
| BigCodeBench Complete | — | 61.1% |
| CadEval | — | 26% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, GPT-4o: 21.0 (#141)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
Reasoning Dolly 2.0-12b leads
Dolly 2.0-12b: 15.3 (#316), GPT-4o: 9.4 (#343)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| LMArena Hard Prompts | 804 | 1281 |
| Epoch Capabilities Index | 89.67 | 128.97 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 17.8% |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| EnigmaEval | — | 0.8% |
| LiveBench Reasoning | — | 55.8% |
| DTBench | — | 64.5% |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 16.6% |
| ForecastBench | — | 57.7 |
| HellaSwag | 70.8% | — |
| LiveBench | — | 55.3% |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), GPT-4o: 10.6 (#312)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| LMArena Math | 871 | 1285 |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| OTIS Mock AIME 2024-2025 | — | 6.4% |
| Omni-MATH | — | 29.3% |
| LiveBench Math | — | 49.5% |
| MATH Level 5 | — | 53.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Not comparable
Dolly 2.0-12b: —, GPT-4o: 28.8 (#242)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| MMLU | 26.2% | 88.1% |
| GPQA Diamond | — | 49.2% |
| Humanity's Last Exam | — | 2.7% |
| SimpleQA Verified | — | 26% |
| MMLU-Pro | — | 71.3% |
| Confabulations | — | 15.3% |
| Vectara Hallucination Rate | — | 9.6% |
| GPQA (HELM) | — | 52% |
| LMArena Expert | — | 1250 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multimodal Not comparable
Dolly 2.0-12b: —, GPT-4o: 34.5 (#91)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| LMArena Vision | — | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual GPT-4o leads
Dolly 2.0-12b: 17.4 (#296), GPT-4o: 43.2 (#186)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| LMArena Non-English | 836 | 1283 |
| LMArena Chinese | 836 | 1277 |
| LMArena French | — | 1304 |
| LMArena German | — | 1282 |
| LMArena Japanese | — | 1257 |
| LMArena Korean | — | 1234 |
| LMArena Russian | — | 1286 |
| LMArena Spanish | — | 1292 |
Instruction Following GPT-4o leads
Dolly 2.0-12b: 38.7 (#304), GPT-4o: 66.6 (#207)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| LMArena Instruction Following | 814 | 1278 |
| LiveBench Instruction Following | — | 68.6% |
| IFEval | — | 81.7% |
Long Context Not comparable
Dolly 2.0-12b: —, GPT-4o: 39.4 (#179)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1289 |
Writing & Preference GPT-4o leads
Dolly 2.0-12b: 15.2 (#311), GPT-4o: 52.6 (#166)
| Benchmark | Dolly 2.0-12b | GPT-4o |
|---|---|---|
| LMArena Text | 851 | 1300 |
| LMArena Creative Writing | 864 | 1292 |
| LMArena Multi-Turn | 740 | 1302 |
| Short-Story Creative Writing | — | 81.8% |
| WildBench | — | 82.8% |
| LiveBench Language | — | 47.6% |
Frequently asked questions
Is Dolly 2.0-12b better than GPT-4o?
GPT-4o is the stronger model overall, scoring 28.6 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or GPT-4o better for coding?
GPT-4o scores higher on coding benchmarks: 24.8 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and GPT-4o share?
11 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and GPT-4o has 72.