Model comparison
DBRX vs Granite 3.1 2b Instruct
Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 29.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
DatabricksSummary
- They share 12 benchmarks with published results for both. DBRX scores higher in 1 category and Granite 3.1 2b Instruct in 7 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.1 2b Instruct leads 30.3 to 14.9.
Side by side
| DBRX | Granite 3.1 2b Instruct | |
|---|---|---|
| Provider | Databricks | IBM |
| Noometry Index | 29.0 | 32.6 |
| Released | 2024-03-27 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DBRX: 32.3 (#262), Granite 3.1 2b Instruct: 32.9 (#255)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Coding | 1132 | 1149 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Reasoning Too close to call
DBRX: 20.5 (#218), Granite 3.1 2b Instruct: 21.0 (#206)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1138 |
Math Granite 3.1 2b Instruct leads
DBRX: 22.3 (#265), Granite 3.1 2b Instruct: 30.6 (#206)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Math | 1145 | 1159 |
| MATH Level 5 | 11.7% | — |
Knowledge Granite 3.1 2b Instruct leads
DBRX: 14.9 (#289), Granite 3.1 2b Instruct: 30.3 (#223)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Expert | 1076 | 1131 |
| GPQA Diamond | 32.9% | — |
Multilingual Too close to call
DBRX: 29.4 (#263), Granite 3.1 2b Instruct: 29.2 (#264)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Non-English | 1071 | 1068 |
| LMArena Chinese | 1068 | 1138 |
| LMArena Russian | 1078 | 1063 |
| LMArena French | 1095 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |
Instruction Following Too close to call
DBRX: 57.7 (#265), Granite 3.1 2b Instruct: 58.0 (#259)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1112 | 1116 |
Long Context Granite 3.1 2b Instruct leads
DBRX: 33.7 (#253), Granite 3.1 2b Instruct: 35.0 (#239)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1112 | 1155 |
Writing & Preference Too close to call
DBRX: 33.7 (#271), Granite 3.1 2b Instruct: 34.3 (#269)
| Benchmark | DBRX | Granite 3.1 2b Instruct |
|---|---|---|
| LMArena Text | 1119 | 1127 |
| LMArena Creative Writing | 1104 | 1116 |
| LMArena Multi-Turn | 1111 | 1099 |
Frequently asked questions
Is DBRX better than Granite 3.1 2b Instruct?
Granite 3.1 2b Instruct is the stronger model overall, scoring 32.6 to 29.0 on the Noometry Index.
Is DBRX or Granite 3.1 2b Instruct better for coding?
They score almost the same on coding (32.3 vs 32.9); test both on your own repository before choosing.
How many benchmarks do DBRX and Granite 3.1 2b Instruct share?
12 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Granite 3.1 2b Instruct has 12.