# DBRX vs DeepSeek V4.1 Flash

> DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-deepseek-v4-1-flash
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and DeepSeek V4.1 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4.1 Flash leads 57.9 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 89.8% for DeepSeek V4.1 Flash.

## Snapshot

| | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| Provider | Databricks | DeepSeek |
| Noometry Index | 29.4 | 52.8 |
| Rank | 311 | 38 |
| Context | — | 1M |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Open |

## Coding

- DBRX: 32.9 (#266)
- DeepSeek V4.1 Flash: 52.9 (#32)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Coding | 1132 | 1506 |
| LMArena WebDev | — | 1619 |
| SciCode | — | 51.9% |
| ALE-Bench | — | 1,092 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Agentic & Tool Use

- DBRX: —
- DeepSeek V4.1 Flash: 31.2 (#69)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | — | 39.5% |
| GDP.pdf | — | 19.8% |

## Reasoning

- DBRX: 21.4 (#222)
- DeepSeek V4.1 Flash: 50.2 (#36)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1483 |
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 14.3% |
| Mystery Game Puzzles | — | 43% |
| DTBench | — | 89.9% |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| Epoch Capabilities Index | — | 154.9 |

## Math

- DBRX: 24.3 (#269)
- DeepSeek V4.1 Flash: 66.7 (#25)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Math | 1145 | 1477 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 26.8% |
| OTIS Mock AIME 2024-2025 | — | 98.3% |
| ProofBench | — | 54% |
| MATH Level 5 | 11.7% | — |

## Knowledge

- DBRX: 14.9 (#294)
- DeepSeek V4.1 Flash: 57.9 (#38)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| GPQA Diamond | 32.9% | 89.8% |
| LMArena Expert | 1076 | 1506 |

## Multimodal

- DBRX: —
- DeepSeek V4.1 Flash: 39.1 (#61)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | — | 1277 |
| Furniture Assembly | — | 34.2% |

## Multilingual

- DBRX: 29.3 (#268)
- DeepSeek V4.1 Flash: 55.0 (#35)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1071 | 1448 |
| LMArena Chinese | 1068 | 1497 |
| LMArena French | 1096 | 1452 |
| LMArena German | 1057 | 1484 |
| LMArena Japanese | 990 | 1412 |
| LMArena Korean | 993 | 1452 |
| LMArena Russian | 1078 | 1471 |
| LMArena Spanish | 1064 | 1459 |

## Instruction Following

- DBRX: 57.5 (#270)
- DeepSeek V4.1 Flash: 77.3 (#26)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1112 | 1474 |

## Long Context

- DBRX: 33.7 (#258)
- DeepSeek V4.1 Flash: 45.2 (#47)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1112 | 1475 |

## Writing & Preference

- DBRX: 33.6 (#275)
- DeepSeek V4.1 Flash: 65.4 (#48)

| Benchmark | DBRX | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1119 | 1462 |
| LMArena Creative Writing | 1104 | 1435 |
| LMArena Multi-Turn | 1111 | 1457 |
| EQ-Bench Creative Writing | — | 1540 |

## FAQ

### Is DBRX better than DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.4 on the Noometry Index.

### Is DBRX or DeepSeek V4.1 Flash better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 32.9 in the Noometry coding category.

### How many benchmarks do DBRX and DeepSeek V4.1 Flash share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and DeepSeek V4.1 Flash has 37.