Model comparison
DBRX vs Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
DatabricksSummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 0 categories and Grok 4.20 Multi-Agent in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.20 Multi-Agent leads 64.0 to 33.6.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| DBRX | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | Databricks | xAI |
| Noometry Index | 29.4 | 46.2 |
| Released | 2024-03-27 | 2026-03-09 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 21 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 Multi-Agent leads
DBRX: 32.9 (#266), Grok 4.20 Multi-Agent: 43.0 (#92)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1132 | 1457 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Grok 4.20 Multi-Agent: —
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | — | 1204 |
Reasoning Grok 4.20 Multi-Agent leads
DBRX: 21.4 (#222), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1448 |
| NYT Connections (extended) | — | 89.6% |
Math Grok 4.20 Multi-Agent leads
DBRX: 24.3 (#269), Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1145 | 1442 |
| MATH Level 5 | 11.7% | — |
Knowledge Grok 4.20 Multi-Agent leads
DBRX: 14.9 (#294), Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1076 | 1445 |
| GPQA Diamond | 32.9% | — |
Multimodal Not comparable
DBRX: —, Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual Grok 4.20 Multi-Agent leads
DBRX: 29.3 (#268), Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1071 | 1440 |
| LMArena Chinese | 1068 | 1475 |
| LMArena French | 1096 | 1466 |
| LMArena German | 1057 | 1456 |
| LMArena Japanese | 990 | 1405 |
| LMArena Korean | 993 | 1416 |
| LMArena Russian | 1078 | 1457 |
| LMArena Spanish | 1064 | 1447 |
Instruction Following Grok 4.20 Multi-Agent leads
DBRX: 57.5 (#270), Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1112 | 1420 |
Long Context Grok 4.20 Multi-Agent leads
DBRX: 33.7 (#258), Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1112 | 1431 |
Writing & Preference Grok 4.20 Multi-Agent leads
DBRX: 33.6 (#275), Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | DBRX | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1119 | 1450 |
| LMArena Creative Writing | 1104 | 1436 |
| LMArena Multi-Turn | 1111 | 1452 |
Frequently asked questions
Is DBRX better than Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 29.4 on the Noometry Index.
Is DBRX or Grok 4.20 Multi-Agent better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Grok 4.20 Multi-Agent share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Grok 4.20 Multi-Agent has 20.