Model comparison
Command R vs DBRX
Command R is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
DatabricksSummary
- They share 17 benchmarks with published results for both. Command R scores higher in 6 categories and DBRX in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 31.0 to 14.9.
Side by side
| Command R | DBRX | |
|---|---|---|
| Provider | Cohere | Databricks |
| Noometry Index | 31.4 | 29.4 |
| Released | 2024-08-30 | 2024-03-27 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
Command R: 29.3 (#306), DBRX: 32.9 (#266)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Coding | 1169 | 1132 |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
| HumanEval+ | — | 70.1% |
| MBPP+ | — | 55.8% |
Reasoning DBRX leads
Command R: 13.8 (#331), DBRX: 21.4 (#222)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1113 |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| LiveBench | 27.5% | — |
Math Command R leads
Command R: 28.0 (#246), DBRX: 24.3 (#269)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Math | 1155 | 1145 |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 11.7% |
Knowledge Command R leads
Command R: 31.0 (#221), DBRX: 14.9 (#294)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Expert | 1138 | 1076 |
| GPQA Diamond | — | 32.9% |
| MMLU | 65.2% | — |
Multilingual Command R leads
Command R: 35.7 (#245), DBRX: 29.3 (#268)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Non-English | 1174 | 1071 |
| LMArena Chinese | 1182 | 1068 |
| LMArena French | 1162 | 1096 |
| LMArena German | 1176 | 1057 |
| LMArena Japanese | 1143 | 990 |
| LMArena Korean | 1163 | 993 |
| LMArena Russian | 1174 | 1078 |
| LMArena Spanish | 1151 | 1064 |
Instruction Following Too close to call
Command R: 58.1 (#261), DBRX: 57.5 (#270)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Instruction Following | 1167 | 1112 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Command R leads
Command R: 36.3 (#231), DBRX: 33.7 (#258)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Longer Query | 1198 | 1112 |
Writing & Preference Command R leads
Command R: 38.2 (#254), DBRX: 33.6 (#275)
| Benchmark | Command R | DBRX |
|---|---|---|
| LMArena Text | 1187 | 1119 |
| LMArena Creative Writing | 1170 | 1104 |
| LMArena Multi-Turn | 1163 | 1111 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than DBRX?
Command R is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.
Is Command R or DBRX better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and DBRX share?
17 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DBRX has 21.