Model comparison
DBRX vs Llama 3.1-405B
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 29.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Databricks
MetaSummary
- They share 19 benchmarks with published results for both. DBRX scores higher in 2 categories and Llama 3.1-405B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 14.9.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 49.8% for Llama 3.1-405B.
Side by side
| DBRX | Llama 3.1-405B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 29.4 | 30.7 |
| Released | 2024-03-27 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.9 (#266), Llama 3.1-405B: 33.1 (#262)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1132 | 1291 |
| WeirdML | — | 21.4% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Llama 3.1-405B: 21.0 (#140)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning DBRX leads
DBRX: 21.4 (#222), Llama 3.1-405B: 16.8 (#300)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1269 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| DTBench | — | 61.4% |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.75 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math DBRX leads
DBRX: 24.3 (#269), Llama 3.1-405B: 18.4 (#290)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1145 | 1281 |
| MATH Level 5 | 11.7% | 49.8% |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
Knowledge Llama 3.1-405B leads
DBRX: 14.9 (#294), Llama 3.1-405B: 30.4 (#227)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 32.9% | 50.9% |
| LMArena Expert | 1076 | 1243 |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multilingual Llama 3.1-405B leads
DBRX: 29.3 (#268), Llama 3.1-405B: 40.7 (#214)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1071 | 1248 |
| LMArena Chinese | 1068 | 1242 |
| LMArena French | 1096 | 1279 |
| LMArena German | 1057 | 1252 |
| LMArena Japanese | 990 | 1208 |
| LMArena Korean | 993 | 1184 |
| LMArena Russian | 1078 | 1265 |
| LMArena Spanish | 1064 | 1260 |
Instruction Following Llama 3.1-405B leads
DBRX: 57.5 (#270), Llama 3.1-405B: 65.9 (#214)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1259 |
| IFEval | — | 81.1% |
Long Context Llama 3.1-405B leads
DBRX: 33.7 (#258), Llama 3.1-405B: 38.4 (#197)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1112 | 1266 |
Writing & Preference Llama 3.1-405B leads
DBRX: 33.6 (#275), Llama 3.1-405B: 38.9 (#251)
| Benchmark | DBRX | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1119 | 1284 |
| LMArena Creative Writing | 1104 | 1262 |
| LMArena Multi-Turn | 1111 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is DBRX better than Llama 3.1-405B?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 29.4 on the Noometry Index.
Is DBRX or Llama 3.1-405B better for coding?
They score almost the same on coding (32.9 vs 33.1); test both on your own repository before choosing.
How many benchmarks do DBRX and Llama 3.1-405B share?
19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 3.1-405B has 42.