# DBRX vs DeepSeek-R1

> DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-deepseek-r1
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. DBRX scores higher in 1 category and DeepSeek-R1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-R1 leads 44.5 to 14.9.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 96.6% for DeepSeek-R1.
- DBRX has downloadable open weights; the other is API-only.

## Snapshot

| | DBRX | DeepSeek-R1 |
|---|---|---|
| Provider | Databricks | DeepSeek |
| Noometry Index | 29.4 | 42.3 |
| Rank | 311 | 115 |
| Context | — | 164K |
| Input $/M | — | $0.50 |
| Output $/M | — | $2.15 |
| Weights | Open | Proprietary |

## Coding

- DBRX: 32.9 (#266)
- DeepSeek-R1: 46.3 (#68)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| LMArena Coding | 1132 | 1427 |
| Aider Polyglot | — | 71.4% |
| SciCode | — | 35.7% |
| WeirdML | — | 41.6% |
| LiveBench Coding | — | 66.7% |
| ALE-Bench | — | 804.12 |
| AlgoTune | — | 1.7 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Agentic & Tool Use

- DBRX: —
- DeepSeek-R1: 30.7 (#75)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| METR Time Horizons | — | 53.8% |

## Reasoning

- DBRX: 21.4 (#222)
- DeepSeek-R1: 18.6 (#278)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1416 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 40.8% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 21.2% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | — | 83.2% |
| LiveBench Data Analysis | — | 69.8% |
| Epoch Capabilities Index | — | 141.29 |
| ForecastBench | — | 60 |
| LiveBench | — | 71.6% |

## Math

- DBRX: 24.3 (#269)
- DeepSeek-R1: 43.8 (#79)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| LMArena Math | 1145 | 1400 |
| MATH Level 5 | 11.7% | 96.6% |
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |

## Knowledge

- DBRX: 14.9 (#294)
- DeepSeek-R1: 44.5 (#87)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| GPQA Diamond | 32.9% | 76.3% |
| LMArena Expert | 1076 | 1394 |
| MMLU-Pro | — | 79.3% |
| Confabulations | — | 12.7% |
| Vectara Hallucination Rate | — | 11.3% |
| GPQA (HELM) | — | 66.6% |

## Multilingual

- DBRX: 29.3 (#268)
- DeepSeek-R1: 52.4 (#85)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1071 | 1412 |
| LMArena Chinese | 1068 | 1442 |
| LMArena French | 1096 | 1417 |
| LMArena German | 1057 | 1404 |
| LMArena Japanese | 990 | 1391 |
| LMArena Korean | 993 | 1360 |
| LMArena Russian | 1078 | 1423 |
| LMArena Spanish | 1064 | 1411 |

## Instruction Following

- DBRX: 57.5 (#270)
- DeepSeek-R1: 72.0 (#143)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1112 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |

## Long Context

- DBRX: 33.7 (#258)
- DeepSeek-R1: 45.4 (#36)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1112 | 1391 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- DBRX: 33.6 (#275)
- DeepSeek-R1: 61.4 (#88)

| Benchmark | DBRX | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1119 | 1428 |
| LMArena Creative Writing | 1104 | 1405 |
| LMArena Multi-Turn | 1111 | 1405 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1500 |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |

## FAQ

### Is DBRX better than DeepSeek-R1?

DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.4 on the Noometry Index.

### Is DBRX or DeepSeek-R1 better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 32.9 in the Noometry coding category.

### How many benchmarks do DBRX and DeepSeek-R1 share?

19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and DeepSeek-R1 has 52.