Model comparison
DBRX vs Llama 3.1-70B
DBRX and Llama 3.1-70B 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 . 19 shared benchmarks.
Databricks
MetaSummary
- They share 19 benchmarks with published results for both. DBRX scores higher in 2 categories and Llama 3.1-70B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 13.5.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 36.7% for Llama 3.1-70B.
Side by side
| DBRX | Llama 3.1-70B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 29.4 | 29.6 |
| Released | 2024-03-27 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 21 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Llama 3.1-70B: 30.3 (#296)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 1132 | 1260 |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Llama 3.1-70B: 25.1 (#112)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
Reasoning Too close to call
DBRX: 21.4 (#222), Llama 3.1-70B: 21.6 (#220)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1241 |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| Epoch Capabilities Index | — | 125.92 |
Math DBRX leads
DBRX: 24.3 (#269), Llama 3.1-70B: 13.5 (#304)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 1145 | 1252 |
| MATH Level 5 | 11.7% | 36.7% |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
Knowledge Llama 3.1-70B leads
DBRX: 14.9 (#294), Llama 3.1-70B: 24.2 (#269)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| GPQA Diamond | 32.9% | 44.2% |
| LMArena Expert | 1076 | 1209 |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |
Multilingual Llama 3.1-70B leads
DBRX: 29.3 (#268), Llama 3.1-70B: 38.8 (#225)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1071 | 1219 |
| LMArena Chinese | 1068 | 1215 |
| LMArena French | 1096 | 1261 |
| LMArena German | 1057 | 1222 |
| LMArena Japanese | 990 | 1132 |
| LMArena Korean | 993 | 1140 |
| LMArena Russian | 1078 | 1234 |
| LMArena Spanish | 1064 | 1253 |
Instruction Following Llama 3.1-70B leads
DBRX: 57.5 (#270), Llama 3.1-70B: 65.3 (#223)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1231 |
| IFEval | — | 82.1% |
Long Context Llama 3.1-70B leads
DBRX: 33.7 (#258), Llama 3.1-70B: 37.6 (#214)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1112 | 1241 |
Writing & Preference Llama 3.1-70B leads
DBRX: 33.6 (#275), Llama 3.1-70B: 35.4 (#267)
| Benchmark | DBRX | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1119 | 1261 |
| LMArena Creative Writing | 1104 | 1232 |
| LMArena Multi-Turn | 1111 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
Frequently asked questions
Is DBRX better than Llama 3.1-70B?
DBRX and Llama 3.1-70B 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 3.1-70B better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 30.3 in the Noometry coding category.
How many benchmarks do DBRX and Llama 3.1-70B share?
19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 3.1-70B has 35.