Model comparison
DBRX vs Llama 3-70B
DBRX and Llama 3-70B score almost the same on the Noometry Index (29.4 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Databricks
MetaSummary
- They share 21 benchmarks with published results for both. DBRX scores higher in 2 categories and Llama 3-70B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 12.8.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 22.6% for Llama 3-70B.
Side by side
| DBRX | Llama 3-70B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 29.4 | 28.8 |
| Released | 2024-03-27 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
DBRX: 32.9 (#266), Llama 3-70B: 35.8 (#218)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1132 | 1206 |
| HumanEval+ | 70.1% | 72% |
| MBPP+ | 55.8% | 69% |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
Agentic & Tool Use Not comparable
DBRX: —, Llama 3-70B: 21.1 (#139)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning DBRX leads
DBRX: 21.4 (#222), Llama 3-70B: 18.0 (#288)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math DBRX leads
DBRX: 24.3 (#269), Llama 3-70B: 12.8 (#305)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| LMArena Math | 1145 | 1218 |
| MATH Level 5 | 11.7% | 22.6% |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
Knowledge Llama 3-70B leads
DBRX: 14.9 (#294), Llama 3-70B: 20.8 (#277)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 32.9% | 40.6% |
| LMArena Expert | 1076 | 1149 |
| MMLU | — | 79.3% |
Multilingual Llama 3-70B leads
DBRX: 29.3 (#268), Llama 3-70B: 33.6 (#251)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1071 | 1142 |
| LMArena Chinese | 1068 | 1114 |
| LMArena French | 1096 | 1232 |
| LMArena German | 1057 | 1169 |
| LMArena Japanese | 990 | 1017 |
| LMArena Korean | 993 | 1017 |
| LMArena Russian | 1078 | 1159 |
| LMArena Spanish | 1064 | 1241 |
Instruction Following Llama 3-70B leads
DBRX: 57.5 (#270), Llama 3-70B: 62.5 (#238)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1194 |
Long Context Llama 3-70B leads
DBRX: 33.7 (#258), Llama 3-70B: 35.6 (#240)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1112 | 1174 |
Writing & Preference Llama 3-70B leads
DBRX: 33.6 (#275), Llama 3-70B: 42.8 (#231)
| Benchmark | DBRX | Llama 3-70B |
|---|---|---|
| LMArena Text | 1119 | 1221 |
| LMArena Creative Writing | 1104 | 1210 |
| LMArena Multi-Turn | 1111 | 1223 |
Frequently asked questions
Is DBRX better than Llama 3-70B?
DBRX and Llama 3-70B score almost the same on the Noometry Index (29.4 vs 28.8), so choose on price, context window or the category you care about most.
Is DBRX or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Llama 3-70B share?
21 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 3-70B has 31.