Model comparison
Dolly 2.0-12b vs Ministral 8B
Ministral 8B is the stronger model overall, scoring 28.2 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
Databricks
Mistral AISummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 1 category and Ministral 8B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Ministral 8B leads 39.6 to 15.2.
Side by side
| Dolly 2.0-12b | Ministral 8B | |
|---|---|---|
| Provider | Databricks | Mistral AI |
| Noometry Index | 25.5 | 28.2 |
| Released | 2023-04-11 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Dolly 2.0-12b: 23.4 (#332), Ministral 8B: 35.0 (#230)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| LMArena Coding | 776 | 1202 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, Ministral 8B: 16.4 (#148)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Ministral 8B leads
Dolly 2.0-12b: 15.3 (#316), Ministral 8B: 18.4 (#281)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 804 | 1191 |
| DTBench | — | 45.7% |
| Epoch Capabilities Index | 89.67 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math Dolly 2.0-12b leads
Dolly 2.0-12b: 27.3 (#251), Ministral 8B: 25.7 (#267)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| LMArena Math | 871 | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Not comparable
Dolly 2.0-12b: —, Ministral 8B: 12.6 (#297)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1170 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual Ministral 8B leads
Dolly 2.0-12b: 17.4 (#296), Ministral 8B: 35.1 (#247)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| LMArena Non-English | 836 | 1165 |
| LMArena Chinese | 836 | 1193 |
| LMArena Russian | — | 1195 |
Instruction Following Ministral 8B leads
Dolly 2.0-12b: 38.7 (#304), Ministral 8B: 60.5 (#250)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 814 | 1161 |
Long Context Not comparable
Dolly 2.0-12b: —, Ministral 8B: 36.7 (#227)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| LMArena Longer Query | — | 1212 |
Writing & Preference Ministral 8B leads
Dolly 2.0-12b: 15.2 (#311), Ministral 8B: 39.6 (#246)
| Benchmark | Dolly 2.0-12b | Ministral 8B |
|---|---|---|
| LMArena Text | 851 | 1191 |
| LMArena Creative Writing | 864 | 1175 |
| LMArena Multi-Turn | 740 | 1166 |
Frequently asked questions
Is Dolly 2.0-12b better than Ministral 8B?
Ministral 8B is the stronger model overall, scoring 28.2 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and Ministral 8B share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Ministral 8B has 17.