Model comparison
Command A vs DBRX
Command A is the stronger model overall, scoring 36.5 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
DatabricksSummary
- They share 17 benchmarks with published results for both. Command A scores higher in 6 categories and DBRX in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command A leads 37.1 to 14.9.
Side by side
| Command A | DBRX | |
|---|---|---|
| Provider | Cohere | Databricks |
| Noometry Index | 36.5 | 29.4 |
| Released | 2025-03-13 | 2024-03-27 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DBRX leads
Command A: 27.2 (#322), DBRX: 32.9 (#266)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Coding | 1330 | 1132 |
| Aider Polyglot | 12% | — |
| HumanEval+ | — | 70.1% |
| MBPP+ | — | 55.8% |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), DBRX: —
| Benchmark | Command A | DBRX |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning DBRX leads
Command A: 18.3 (#283), DBRX: 21.4 (#222)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1113 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Command A leads
Command A: 36.2 (#171), DBRX: 24.3 (#269)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Math | 1300 | 1145 |
| MATH Level 5 | — | 11.7% |
Knowledge Command A leads
Command A: 37.1 (#159), DBRX: 14.9 (#294)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Expert | 1295 | 1076 |
| GPQA Diamond | — | 32.9% |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual Command A leads
Command A: 45.3 (#170), DBRX: 29.3 (#268)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Non-English | 1313 | 1071 |
| LMArena Chinese | 1327 | 1068 |
| LMArena French | 1351 | 1096 |
| LMArena German | 1341 | 1057 |
| LMArena Japanese | 1285 | 990 |
| LMArena Korean | 1285 | 993 |
| LMArena Russian | 1314 | 1078 |
| LMArena Spanish | 1347 | 1064 |
Instruction Following Command A leads
Command A: 69.1 (#177), DBRX: 57.5 (#270)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Instruction Following | 1309 | 1112 |
Long Context Command A leads
Command A: 40.6 (#151), DBRX: 33.7 (#258)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Longer Query | 1334 | 1112 |
Writing & Preference Command A leads
Command A: 47.6 (#208), DBRX: 33.6 (#275)
| Benchmark | Command A | DBRX |
|---|---|---|
| LMArena Text | 1331 | 1119 |
| LMArena Creative Writing | 1319 | 1104 |
| LMArena Multi-Turn | 1339 | 1111 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than DBRX?
Command A is the stronger model overall, scoring 36.5 to 29.4 on the Noometry Index.
Is Command A or DBRX better for coding?
DBRX scores higher on coding benchmarks: 32.9 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and DBRX share?
17 benchmarks have published results for both models. Command A has 24 scored results on Noometry and DBRX has 21.