Model comparison
DBRX vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 29.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
DatabricksSummary
- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.6 leads 63.3 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 94% for Grok 4.6.
- DBRX has downloadable open weights; the other is API-only.
Side by side
| DBRX | Grok 4.6 | |
|---|---|---|
| Provider | Databricks | xAI |
| Noometry Index | 29.4 | 56.9 |
| Released | 2024-03-27 | 2026-08-12 |
| Weights | Open | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 21 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
DBRX: 32.9 (#266), Grok 4.6: 58.5 (#16)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Coding | 1132 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| WeirdML | — | 67.3% |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Grok 4.6: 39.4 (#27)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
DBRX: 21.4 (#222), Grok 4.6: 61.4 (#20)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1447 |
| ARC-AGI-2 | — | 67.1% |
| SimpleBench | — | 75.9% |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.3% |
| LMCA | — | 48.5% |
| Epoch Capabilities Index | — | 156.44 |
Math Grok 4.6 leads
DBRX: 24.3 (#269), Grok 4.6: 67.0 (#24)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Math | 1145 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 51% |
| MATH Level 5 | 11.7% | — |
Knowledge Grok 4.6 leads
DBRX: 14.9 (#294), Grok 4.6: 63.3 (#20)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 32.9% | 94% |
| LMArena Expert | 1076 | 1467 |
| SimpleQA Verified | — | 49.3% |
Multimodal Not comparable
DBRX: —, Grok 4.6: 43.6 (#23)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
DBRX: 29.3 (#268), Grok 4.6: 53.0 (#74)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1071 | 1420 |
| LMArena Chinese | 1068 | 1480 |
| LMArena French | 1096 | 1461 |
| LMArena German | 1057 | 1431 |
| LMArena Japanese | 990 | 1376 |
| LMArena Korean | 993 | 1397 |
| LMArena Russian | 1078 | 1422 |
| LMArena Spanish | 1064 | 1404 |
Instruction Following Grok 4.6 leads
DBRX: 57.5 (#270), Grok 4.6: 75.4 (#63)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1112 | 1431 |
Long Context Grok 4.6 leads
DBRX: 33.7 (#258), Grok 4.6: 44.5 (#66)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1112 | 1454 |
Writing & Preference Grok 4.6 leads
DBRX: 33.6 (#275), Grok 4.6: 62.3 (#80)
| Benchmark | DBRX | Grok 4.6 |
|---|---|---|
| LMArena Text | 1119 | 1428 |
| LMArena Creative Writing | 1104 | 1428 |
| LMArena Multi-Turn | 1111 | 1425 |
Frequently asked questions
Is DBRX better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 29.4 on the Noometry Index.
Is DBRX or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Grok 4.6 share?
18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Grok 4.6 has 49.