Model comparison
Dolly 2.0-12b vs Mixtral 8x7B
Mixtral 8x7B is the stronger model overall, scoring 27.1 to 25.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
Databricks
Mistral AISummary
- They share 16 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and Mixtral 8x7B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mixtral 8x7B leads 34.2 to 15.2.
Side by side
| Dolly 2.0-12b | Mixtral 8x7B | |
|---|---|---|
| Provider | Databricks | Mistral AI |
| Noometry Index | 25.5 | 27.1 |
| Released | 2023-04-11 | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 32K |
| Max output | — | 32K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 17 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
Dolly 2.0-12b: 23.4 (#332), Mixtral 8x7B: 32.8 (#269)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 776 | 1126 |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Reasoning Mixtral 8x7B leads
Dolly 2.0-12b: 15.3 (#316), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1115 |
| Epoch Capabilities Index | 89.67 | 118.47 |
| HellaSwag | 70.8% | 86.7% |
| PIQA | 75.4% | 83.6% |
| WinoGrande | 61.8% | 77.2% |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 871 | 1147 |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge Not comparable
Dolly 2.0-12b: —, Mixtral 8x7B: 11.0 (#301)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| ARC (AI2) Challenge | 39.6% | 87.3% |
| MMLU | 26.2% | 70.6% |
| OpenBookQA | 39.2% | 85.8% |
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| LMArena Expert | — | 1088 |
| BoolQ | 56.3% | — |
| TriviaQA | — | 82.2% |
Multilingual Mixtral 8x7B leads
Dolly 2.0-12b: 17.4 (#296), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 836 | 1077 |
| LMArena Chinese | 836 | 1055 |
| LMArena French | — | 1166 |
| LMArena German | — | 1114 |
| LMArena Japanese | — | 931 |
| LMArena Korean | — | 968 |
| LMArena Russian | — | 1090 |
| LMArena Spanish | — | 1111 |
Instruction Following Mixtral 8x7B leads
Dolly 2.0-12b: 38.7 (#304), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 814 | 1109 |
| IFEval | — | 57.5% |
Long Context Not comparable
Dolly 2.0-12b: —, Mixtral 8x7B: 33.4 (#260)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | — | 1103 |
Writing & Preference Mixtral 8x7B leads
Dolly 2.0-12b: 15.2 (#311), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Dolly 2.0-12b | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 851 | 1132 |
| LMArena Creative Writing | 864 | 1109 |
| LMArena Multi-Turn | 740 | 1115 |
| WildBench | — | 67.3% |
Frequently asked questions
Is Dolly 2.0-12b better than Mixtral 8x7B?
Mixtral 8x7B is the stronger model overall, scoring 27.1 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Mixtral 8x7B better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Mixtral 8x7B share?
16 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Mixtral 8x7B has 38.