Model comparison
DBRX vs Mistral 7B
DBRX is the stronger model overall, scoring 29.4 to 23.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Databricks
Mistral AISummary
- They share 20 benchmarks with published results for both. DBRX scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 8.1.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 15.2% for Mistral 7B.
Side by side
| DBRX | Mistral 7B | |
|---|---|---|
| Provider | Databricks | Mistral AI |
| Noometry Index | 29.4 | 23.0 |
| Released | 2024-03-27 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 21 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Mistral 7B: 26.4 (#326)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| LMArena Coding | 1132 | 1082 |
| HumanEval+ | 70.1% | 36% |
| MBPP+ | 55.8% | 42.1% |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
Reasoning DBRX leads
DBRX: 21.4 (#222), Mistral 7B: 13.1 (#336)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1067 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 112.21 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math DBRX leads
DBRX: 24.3 (#269), Mistral 7B: 8.1 (#325)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| LMArena Math | 1145 | 1085 |
| MATH Level 5 | 11.7% | 3.7% |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| GSM8K | — | 54.4% |
Knowledge DBRX leads
DBRX: 14.9 (#294), Mistral 7B: 7.4 (#311)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| GPQA Diamond | 32.9% | 15.2% |
| LMArena Expert | 1076 | 1036 |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual DBRX leads
DBRX: 29.3 (#268), Mistral 7B: 25.8 (#283)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1071 | 1012 |
| LMArena Chinese | 1068 | 1009 |
| LMArena French | 1096 | 1037 |
| LMArena German | 1057 | 987 |
| LMArena Japanese | 990 | 878 |
| LMArena Russian | 1078 | 1018 |
| LMArena Spanish | 1064 | 1026 |
| LMArena Korean | 993 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Mistral 7B: 54.2 (#280)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1060 |
Long Context DBRX leads
DBRX: 33.7 (#258), Mistral 7B: 32.2 (#271)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1112 | 1060 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Mistral 7B: 30.7 (#286)
| Benchmark | DBRX | Mistral 7B |
|---|---|---|
| LMArena Text | 1119 | 1090 |
| LMArena Creative Writing | 1104 | 1068 |
| LMArena Multi-Turn | 1111 | 1062 |
Frequently asked questions
Is DBRX better than Mistral 7B?
DBRX is the stronger model overall, scoring 29.4 to 23.0 on the Noometry Index.
Is DBRX or Mistral 7B better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 26.4 in the Noometry coding category.
How many benchmarks do DBRX and Mistral 7B share?
20 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Mistral 7B has 37.