Model comparison
DBRX vs Llama 3.2 90B
DBRX is the stronger model overall, scoring 29.4 to 27.5 on the Noometry Index.
Last verified . 2 shared benchmarks.
Databricks
MetaSummary
- They share 2 benchmarks with published results for both. DBRX scores higher in 1 category and Llama 3.2 90B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where DBRX leads 24.3 to 11.1.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 39.4% for Llama 3.2 90B.
Side by side
| DBRX | Llama 3.2 90B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 29.4 | 27.5 |
| Released | 2024-03-27 | 2024-09-24 |
| 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 Not comparable
DBRX: 32.9 (#266), Llama 3.2 90B: —
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| LMArena Coding | 1132 | — |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Llama 3.2 90B: 30.0 (#80)
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
Reasoning Too close to call
DBRX: 21.4 (#222), Llama 3.2 90B: 21.7 (#217)
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1113 | — |
| Epoch Capabilities Index | — | 125.5 |
Math DBRX leads
DBRX: 24.3 (#269), Llama 3.2 90B: 11.1 (#308)
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| MATH Level 5 | 11.7% | 39.4% |
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1145 | — |
Knowledge Llama 3.2 90B leads
DBRX: 14.9 (#294), Llama 3.2 90B: 21.7 (#274)
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 32.9% | 41% |
| LMArena Expert | 1076 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
DBRX: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
DBRX: 29.3 (#268), Llama 3.2 90B: —
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1071 | — |
| LMArena Chinese | 1068 | — |
| LMArena French | 1096 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Russian | 1078 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Not comparable
DBRX: 57.5 (#270), Llama 3.2 90B: —
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1112 | — |
Long Context Not comparable
DBRX: 33.7 (#258), Llama 3.2 90B: —
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1112 | — |
Writing & Preference Not comparable
DBRX: 33.6 (#275), Llama 3.2 90B: —
| Benchmark | DBRX | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1119 | — |
| LMArena Creative Writing | 1104 | — |
| LMArena Multi-Turn | 1111 | — |
Frequently asked questions
Is DBRX better than Llama 3.2 90B?
DBRX is the stronger model overall, scoring 29.4 to 27.5 on the Noometry Index.
How many benchmarks do DBRX and Llama 3.2 90B share?
2 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 3.2 90B has 9.