Model comparison
DBRX vs Llama 3.2 3B
DBRX and Llama 3.2 3B score almost the same on the Noometry Index (29.4 vs 28.9), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Databricks
MetaSummary
- They share 13 benchmarks with published results for both. DBRX scores higher in 6 categories and Llama 3.2 3B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 3B leads 29.7 to 14.9.
Side by side
| DBRX | Llama 3.2 3B | |
|---|---|---|
| Provider | Databricks | Meta |
| Noometry Index | 29.4 | 28.9 |
| Released | 2024-03-27 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 21 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
DBRX: 32.9 (#266), Llama 3.2 3B: 27.6 (#319)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1132 | 1098 |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Llama 3.2 3B: 20.1 (#143)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
Reasoning Too close to call
DBRX: 21.4 (#222), Llama 3.2 3B: 21.0 (#228)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1095 |
Math Llama 3.2 3B leads
DBRX: 24.3 (#269), Llama 3.2 3B: 32.4 (#214)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1145 | 1126 |
| MATH Level 5 | 11.7% | — |
Knowledge Llama 3.2 3B leads
DBRX: 14.9 (#294), Llama 3.2 3B: 29.7 (#235)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1076 | 1090 |
| GPQA Diamond | 32.9% | — |
Multilingual DBRX leads
DBRX: 29.3 (#268), Llama 3.2 3B: 26.2 (#281)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1071 | 1019 |
| LMArena Chinese | 1068 | 1017 |
| LMArena German | 1057 | 1056 |
| LMArena Russian | 1078 | 949 |
| LMArena French | 1096 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following DBRX leads
DBRX: 57.5 (#270), Llama 3.2 3B: 56.0 (#275)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1089 |
Long Context Too close to call
DBRX: 33.7 (#258), Llama 3.2 3B: 33.4 (#261)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1112 | 1100 |
Writing & Preference DBRX leads
DBRX: 33.6 (#275), Llama 3.2 3B: 24.7 (#307)
| Benchmark | DBRX | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1119 | 1110 |
| LMArena Creative Writing | 1104 | 1094 |
| LMArena Multi-Turn | 1111 | 1105 |
| EQ-Bench Creative Writing | — | 595 |
Frequently asked questions
Is DBRX better than Llama 3.2 3B?
DBRX and Llama 3.2 3B score almost the same on the Noometry Index (29.4 vs 28.9), so choose on price, context window or the category you care about most.
Is DBRX or Llama 3.2 3B better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 27.6 in the Noometry coding category.
How many benchmarks do DBRX and Llama 3.2 3B share?
13 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Llama 3.2 3B has 18.