Model comparison
Dolly 2.0-12b vs GPT-4
GPT-4 is the stronger model overall, scoring 29.1 to 25.5 on the Noometry Index.
Last verified . 13 shared benchmarks.
DatabricksSummary
- They share 13 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and GPT-4 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-4 leads 65.3 to 38.7.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Dolly 2.0-12b | GPT-4 | |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 25.5 | 29.1 |
| Released | 2023-04-11 | 2023-03-14 |
| Weights | Open | Proprietary |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $60 |
| Results tracked | 17 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 leads
Dolly 2.0-12b: 23.4 (#332), GPT-4: 31.6 (#283)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| LMArena Coding | 776 | 1254 |
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| HumanEval+ | — | 79.3% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, GPT-4: —
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |
Reasoning GPT-4 leads
Dolly 2.0-12b: 15.3 (#316), GPT-4: 17.8 (#289)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1241 |
| Epoch Capabilities Index | 89.67 | 125.89 |
| HellaSwag | 70.8% | 95.3% |
| WinoGrande | 61.8% | 87.5% |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| ForecastBench | — | 57.8 |
| PIQA | 75.4% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), GPT-4: 10.8 (#309)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| LMArena Math | 871 | 1269 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |
Knowledge Not comparable
Dolly 2.0-12b: —, GPT-4: 18.4 (#282)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| MMLU | 26.2% | 86.4% |
| GPQA Diamond | — | 35.7% |
| LMArena Expert | — | 1211 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
| TriviaQA | — | 84.8% |
Multilingual GPT-4 leads
Dolly 2.0-12b: 17.4 (#296), GPT-4: 40.6 (#215)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| LMArena Non-English | 836 | 1246 |
| LMArena Chinese | 836 | 1242 |
| LMArena French | — | 1283 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1184 |
| LMArena Russian | — | 1251 |
| LMArena Spanish | — | 1261 |
Instruction Following GPT-4 leads
Dolly 2.0-12b: 38.7 (#304), GPT-4: 65.3 (#222)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 814 | 1241 |
Long Context Not comparable
Dolly 2.0-12b: —, GPT-4: 37.7 (#212)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| LMArena Longer Query | — | 1244 |
Writing & Preference GPT-4 leads
Dolly 2.0-12b: 15.2 (#311), GPT-4: 34.9 (#268)
| Benchmark | Dolly 2.0-12b | GPT-4 |
|---|---|---|
| LMArena Text | 851 | 1263 |
| LMArena Creative Writing | 864 | 1244 |
| LMArena Multi-Turn | 740 | 1257 |
| EQ-Bench Creative Writing | — | 752 |
Frequently asked questions
Is Dolly 2.0-12b better than GPT-4?
GPT-4 is the stronger model overall, scoring 29.1 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or GPT-4 better for coding?
GPT-4 scores higher on coding benchmarks: 31.6 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and GPT-4 share?
13 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and GPT-4 has 38.