Model comparison
DBRX vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
Databricks
NVIDIASummary
- They share 9 benchmarks with published results for both. DBRX scores higher in 6 categories and Llama2 70b Steerlm Chat in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama2 70b Steerlm Chat leads 31.3 to 24.3.
Side by side
| DBRX | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Databricks | NVIDIA |
| Noometry Index | 29.4 | 31.8 |
| Released | 2024-03-27 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1132 | 1025 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning DBRX leads
DBRX: 21.4 (#222), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1047 |
Math Llama2 70b Steerlm Chat leads
DBRX: 24.3 (#269), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1145 | 1072 |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
DBRX: 14.9 (#294), Llama2 70b Steerlm Chat: —
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |
Multilingual Too close to call
DBRX: 29.3 (#268), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1071 | 1063 |
| LMArena Chinese | 1068 | — |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Russian | 1078 | — |
| LMArena Spanish | 1064 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1112 | 1060 |
Long Context DBRX leads
DBRX: 33.7 (#258), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1112 | 998 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | DBRX | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1119 | 1098 |
| LMArena Creative Writing | 1104 | 1091 |
| LMArena Multi-Turn | 1111 | 1058 |
Frequently asked questions
Is DBRX better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.4 on the Noometry Index.
Is DBRX or Llama2 70b Steerlm Chat better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 29.9 in the Noometry coding category.
How many benchmarks do DBRX and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama2 70b Steerlm Chat has 9.