Model comparison
Dolly 2.0-12b vs Mixtral 8x22B
Mixtral 8x22B is the stronger model overall, scoring 26.7 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Databricks
Mistral AISummary
- They share 11 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and Mixtral 8x22B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mixtral 8x22B leads 37.1 to 15.3.
Side by side
| Dolly 2.0-12b | Mixtral 8x22B | |
|---|---|---|
| Provider | Databricks | Mistral AI |
| Noometry Index | 24.9 | 26.7 |
| Released | 2023-04-11 | 2024-04-17 |
| Weights | Open | Open |
| Context window | — | 64K |
| Max output | — | 64K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 17 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Dolly 2.0-12b: 23.0 (#327), Mixtral 8x22B: 23.8 (#324)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 776 | 1166 |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Mixtral 8x22B: 22.8 (#119)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Mixtral 8x22B leads
Dolly 2.0-12b: 14.6 (#315), Mixtral 8x22B: 19.1 (#246)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1150 |
| Epoch Capabilities Index | 88.94 | 122 |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 25.0 (#250), Mixtral 8x22B: 21.2 (#271)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 871 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Not comparable
Dolly 2.0-12b: —, Mixtral 8x22B: 15.1 (#288)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| MMLU | 26.2% | 77.8% |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| LMArena Expert | — | 1113 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| OpenBookQA | 39.2% | — |
Multilingual Mixtral 8x22B leads
Dolly 2.0-12b: 17.4 (#291), Mixtral 8x22B: 32.9 (#250)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 836 | 1128 |
| LMArena Chinese | 836 | 1116 |
| LMArena French | — | 1165 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1056 |
| LMArena Russian | — | 1158 |
| LMArena Spanish | — | 1150 |
Instruction Following Mixtral 8x22B leads
Dolly 2.0-12b: 38.9 (#299), Mixtral 8x22B: 57.9 (#261)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 814 | 1147 |
| IFEval | — | 72.4% |
Long Context Not comparable
Dolly 2.0-12b: —, Mixtral 8x22B: 34.6 (#242)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | — | 1144 |
Writing & Preference Mixtral 8x22B leads
Dolly 2.0-12b: 15.3 (#306), Mixtral 8x22B: 37.1 (#257)
| Benchmark | Dolly 2.0-12b | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 851 | 1162 |
| LMArena Creative Writing | 864 | 1141 |
| LMArena Multi-Turn | 740 | 1130 |
| WildBench | — | 71.1% |
Frequently asked questions
Is Dolly 2.0-12b better than Mixtral 8x22B?
Mixtral 8x22B is the stronger model overall, scoring 26.7 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or Mixtral 8x22B better for coding?
They score almost the same on coding (23.0 vs 23.8); test both on your own repository before choosing.
How many benchmarks do Dolly 2.0-12b and Mixtral 8x22B share?
11 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Mixtral 8x22B has 34.