Databricks, open weights
DBRX
DBRX by Databricks ranks 311th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.4. Its strongest category is reasoning, where it ranks 222nd.
Last verified
Specifications
- Noometry rank
- #311 of 354
- Index score
- 29.4
- Evidence
- Confirmed 21 results
- Provider
Databricks- Released
- March 27, 2024
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- —
- Max output
- —
- Input price
- Not listed
- Output price
- Not listed
- Blended price
- Not listed
- Output speed
- Not measured
- Value
- Not ranked
- Knowledge cutoff
- Unknown
Category scores
Each category score combines every public result we have in that category.
- Coding 32.9
- Reasoning 21.4
- Math 24.3
- Knowledge 14.9
- Multilingual 29.3
- Instruction Following 57.5
- Long Context 33.7
- Writing & Preference 33.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 32.9 | #266 | 1 |
| Reasoning | 21.4 | #222 | 1 |
| Math | 24.3 | #269 | 2 |
| Knowledge | 14.9 | #294 | 2 |
| Multilingual | 29.3 | #268 | 1 |
| Instruction Following | 57.5 | #270 | 1 |
| Long Context | 33.7 | #258 | 1 |
| Writing & Preference | 33.6 | #275 | 3 |
Strengths and weaknesses
Categories where DBRX places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Knowledge | 14.9 | −22.4 | #294 of 314, top 94% |
| Multilingual | 29.3 | −18.2 | #268 of 297, top 91% |
| Instruction Following | 57.5 | −13.8 | #270 of 305, top 89% |
Closest competitors
The models ranked just above and below DBRX. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemma 2B | #307 | 29.6 | — | — | Compare |
| Llama 3.1-70B | #308 | 29.6 | $0.40 | — | Compare |
| Llama 2-13B | #309 | 29.6 | — | — | Compare |
| Claude 3 Opus | #310 | 29.5 | — | — | Compare |
| Gemma 2 27B | #312 | 29.4 | $0.65 | — | Compare |
| Gemma 1.1 2b IT | #313 | 29.3 | — | — | Compare |
| Phi 3 Small 8k Instruct | #314 | 29.3 | — | — | Compare |
| Claude 3.5 Haiku | #315 | 29.2 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 1132 | #261 of 294, top 89% | LMArena | 2026-10-08 | |
| HumanEval+ | 70.1% | #21 of 45, top 47% | EvalPlus | ||
| MBPP+ | 55.8% | #27 of 38, top 72% | EvalPlus |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1113 | #263 of 297, top 89% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1145 | #254 of 285, top 90% | LMArena | 2026-10-08 | |
| MATH Level 5 | 11.7% | #71 of 79, top 90% | Epoch AI | 2025-01-27 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 32.9% | #166 of 186, top 90% | Epoch AI | 2025-01-27 | |
| LMArena Expert | 1076 | #255 of 273, top 94% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1071 | #268 of 297, top 91% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1068 | #262 of 285, top 92% | LMArena | 2026-10-08 | |
| LMArena French | 1096 | #214 of 223, top 96% | LMArena | 2026-10-08 | |
| LMArena German | 1057 | #217 of 231, top 94% | LMArena | 2026-10-08 | |
| LMArena Japanese | 990 | #201 of 211, top 96% | LMArena | 2026-10-08 | |
| LMArena Korean | 993 | #202 of 213, top 95% | LMArena | 2026-10-08 | |
| LMArena Russian | 1078 | #262 of 283, top 93% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1064 | #222 of 226, top 99% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1112 | #265 of 298, top 89% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1112 | #265 of 291, top 92% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1119 | #268 of 297, top 91% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1104 | #264 of 295, top 90% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1111 | #262 of 295, top 89% | LMArena | 2026-10-08 |
Compare DBRX
Other Databricks models
- Dolly 2.0-12b25.5
Frequently asked questions
How good is DBRX?
DBRX by Databricks ranks 311th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.4. Its strongest category is reasoning, where it ranks 222nd.
Is DBRX open source?
Yes. DBRX's weights are downloadable; check the license for commercial terms.
What are DBRX's strengths and weaknesses?
Relative to other ranked models, DBRX places best in reasoning, coding, math and lowest in knowledge, multilingual, instruction following.
What is DBRX best at?
Its best category is reasoning, where it ranks 222nd on Noometry.