Model comparison
DBRX vs Llama 2-13B
DBRX and Llama 2-13B score almost the same on the Noometry Index (29.4 vs 29.6), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Databricks
MetaSummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 6 categories and Llama 2-13B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-13B leads 28.1 to 14.9.
Side by side
| DBRX | Llama 2-13B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 29.4 | 29.6 |
| Released | 2024-03-27 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Llama 2-13B: 30.9 (#291)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1132 | 1062 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Llama 2-13B: 12.8 (#337)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1051 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 106.17 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
DBRX: 24.3 (#269), Llama 2-13B: 31.1 (#229)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Math | 1145 | 1065 |
| MATH Level 5 | 11.7% | — |
| GSM8K | — | 36.9% |
Knowledge Llama 2-13B leads
DBRX: 14.9 (#294), Llama 2-13B: 28.1 (#249)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1076 | 1030 |
| GPQA Diamond | 32.9% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
DBRX: —, Llama 2-13B: —
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual DBRX leads
DBRX: 29.3 (#268), Llama 2-13B: 26.5 (#279)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1071 | 1024 |
| LMArena Chinese | 1068 | 1001 |
| LMArena French | 1096 | 1044 |
| LMArena German | 1057 | 1009 |
| LMArena Japanese | 990 | 894 |
| LMArena Korean | 993 | 953 |
| LMArena Russian | 1078 | 1055 |
| LMArena Spanish | 1064 | 1087 |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Llama 2-13B: 53.3 (#287)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1045 |
Long Context DBRX leads
DBRX: 33.7 (#258), Llama 2-13B: 32.3 (#269)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1112 | 1064 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Llama 2-13B: 29.8 (#289)
| Benchmark | DBRX | Llama 2-13B |
|---|---|---|
| LMArena Text | 1119 | 1084 |
| LMArena Creative Writing | 1104 | 1047 |
| LMArena Multi-Turn | 1111 | 1050 |
Frequently asked questions
Is DBRX better than Llama 2-13B?
DBRX and Llama 2-13B score almost the same on the Noometry Index (29.4 vs 29.6), so choose on price, context window or the category you care about most.
Is DBRX or Llama 2-13B better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 30.9 in the Noometry coding category.
How many benchmarks do DBRX and Llama 2-13B share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 2-13B has 32.