Model comparison
DBRX vs Llama 2-7B
DBRX and Llama 2-7B score almost the same on the Noometry Index (29.4 vs 29.1), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
Databricks
MetaSummary
- They share 15 benchmarks with published results for both. DBRX scores higher in 6 categories and Llama 2-7B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-7B leads 28.2 to 14.9.
Side by side
| DBRX | Llama 2-7B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 29.4 | 29.1 |
| Released | 2024-03-27 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Llama 2-7B: 29.2 (#307)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1132 | 1002 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Llama 2-7B: 15.7 (#312)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1009 |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | — | 39.2% |
| Epoch Capabilities Index | — | 99.06 |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Llama 2-7B leads
DBRX: 24.3 (#269), Llama 2-7B: 30.7 (#233)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Math | 1145 | 1042 |
| MATH Level 5 | 11.7% | — |
| GSM8K | — | 16.7% |
Knowledge Llama 2-7B leads
DBRX: 14.9 (#294), Llama 2-7B: 28.2 (#248)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1076 | 1036 |
| GPQA Diamond | 32.9% | — |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
DBRX: —, Llama 2-7B: —
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual DBRX leads
DBRX: 29.3 (#268), Llama 2-7B: 23.8 (#293)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1071 | 973 |
| LMArena Chinese | 1068 | 973 |
| LMArena French | 1096 | 970 |
| LMArena German | 1057 | 978 |
| LMArena Russian | 1078 | 995 |
| LMArena Spanish | 1064 | 1007 |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Llama 2-7B: 50.8 (#298)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1006 |
Long Context DBRX leads
DBRX: 33.7 (#258), Llama 2-7B: 30.4 (#287)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1112 | 999 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Llama 2-7B: 28.0 (#298)
| Benchmark | DBRX | Llama 2-7B |
|---|---|---|
| LMArena Text | 1119 | 1053 |
| LMArena Creative Writing | 1104 | 1033 |
| LMArena Multi-Turn | 1111 | 1029 |
Frequently asked questions
Is DBRX better than Llama 2-7B?
DBRX and Llama 2-7B score almost the same on the Noometry Index (29.4 vs 29.1), so choose on price, context window or the category you care about most.
Is DBRX or Llama 2-7B better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 29.2 in the Noometry coding category.
How many benchmarks do DBRX and Llama 2-7B share?
15 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 2-7B has 29.