Model comparison
Dolly 2.0-12b vs Mistral 7B
Dolly 2.0-12b is the stronger model overall, scoring 25.5 to 23.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
Mistral AISummary
- They share 17 benchmarks with published results for both. Dolly 2.0-12b scores higher in 2 categories and Mistral 7B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Dolly 2.0-12b leads 27.3 to 8.1.
Side by side
| Dolly 2.0-12b | Mistral 7B | |
|---|---|---|
| Provider | Databricks | Mistral AI |
| Noometry Index | 25.5 | 23.0 |
| Released | 2023-04-11 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 17 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral 7B leads
Dolly 2.0-12b: 23.4 (#332), Mistral 7B: 26.4 (#326)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| LMArena Coding | 776 | 1082 |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Dolly 2.0-12b leads
Dolly 2.0-12b: 15.3 (#316), Mistral 7B: 13.1 (#336)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1067 |
| Epoch Capabilities Index | 89.67 | 112.21 |
| HellaSwag | 70.8% | 81% |
| PIQA | 75.4% | 83% |
| WinoGrande | 61.8% | 75.3% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), Mistral 7B: 8.1 (#325)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| LMArena Math | 871 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Not comparable
Dolly 2.0-12b: —, Mistral 7B: 7.4 (#311)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 78.6% |
| BoolQ | 56.3% | 87.4% |
| MMLU | 26.2% | 62.5% |
| OpenBookQA | 39.2% | 79.8% |
| GPQA Diamond | — | 15.2% |
| LMArena Expert | — | 1036 |
| TriviaQA | — | 75.2% |
Multilingual Mistral 7B leads
Dolly 2.0-12b: 17.4 (#296), Mistral 7B: 25.8 (#283)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| LMArena Non-English | 836 | 1012 |
| LMArena Chinese | 836 | 1009 |
| LMArena French | — | 1037 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Russian | — | 1018 |
| LMArena Spanish | — | 1026 |
Instruction Following Mistral 7B leads
Dolly 2.0-12b: 38.7 (#304), Mistral 7B: 54.2 (#280)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 814 | 1060 |
Long Context Not comparable
Dolly 2.0-12b: —, Mistral 7B: 32.2 (#271)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| LMArena Longer Query | — | 1060 |
Writing & Preference Mistral 7B leads
Dolly 2.0-12b: 15.2 (#311), Mistral 7B: 30.7 (#286)
| Benchmark | Dolly 2.0-12b | Mistral 7B |
|---|---|---|
| LMArena Text | 851 | 1090 |
| LMArena Creative Writing | 864 | 1068 |
| LMArena Multi-Turn | 740 | 1062 |
Frequently asked questions
Is Dolly 2.0-12b better than Mistral 7B?
Dolly 2.0-12b is the stronger model overall, scoring 25.5 to 23.0 on the Noometry Index.
Is Dolly 2.0-12b or Mistral 7B better for coding?
Mistral 7B scores higher on coding benchmarks: 26.4 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Mistral 7B share?
17 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Mistral 7B has 37.