# DBRX vs DeepSeek-V3.1-Terminus

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-deepseek-v3-1-terminus
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DBRX scores higher in 0 categories and DeepSeek-V3.1-Terminus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 33.7.

## Snapshot

| | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| Provider | Databricks | DeepSeek |
| Noometry Index | 29.0 | 42.6 |
| Rank | 307 | 96 |
| Context | — | 164K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1 |
| Weights | Open | Open |

## Coding

- DBRX: 32.3 (#262)
- DeepSeek-V3.1-Terminus: 41.5 (#114)

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1132 | 1426 |
| SciCode | — | 40.6% |
| ALE-Bench | — | 745.17 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Reasoning

- DBRX: 20.5 (#218)
- DeepSeek-V3.1-Terminus: 25.7 (#126)

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1427 |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| DTBench | — | 81.3% |
| LMCA | — | 28.6% |

## Math

- DBRX: 22.3 (#265)
- DeepSeek-V3.1-Terminus: 35.7 (#138)

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1145 | 1402 |
| MATH Level 5 | 11.7% | — |

## Knowledge

- DBRX: 14.9 (#289)
- DeepSeek-V3.1-Terminus: —

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| GPQA Diamond | 32.9% | — |
| LMArena Expert | 1076 | — |

## Multilingual

- DBRX: 29.4 (#263)
- DeepSeek-V3.1-Terminus: 52.3 (#87)

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1071 | 1407 |
| LMArena Russian | 1078 | 1434 |
| LMArena Chinese | 1068 | — |
| LMArena French | 1095 | — |
| LMArena German | 1057 | — |
| LMArena Japanese | 990 | — |
| LMArena Korean | 993 | — |
| LMArena Spanish | 1064 | — |

## Instruction Following

- DBRX: 57.7 (#265)
- DeepSeek-V3.1-Terminus: 74.4 (#96)

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1112 | 1406 |

## Long Context

- DBRX: 33.7 (#253)
- DeepSeek-V3.1-Terminus: 43.5 (#88)

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1112 | 1426 |

## Writing & Preference

- DBRX: 33.7 (#271)
- DeepSeek-V3.1-Terminus: 61.3 (#87)

| Benchmark | DBRX | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1119 | 1420 |
| LMArena Creative Writing | 1104 | 1404 |
| LMArena Multi-Turn | 1111 | 1411 |

## FAQ

### Is DBRX better than DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.0 on the Noometry Index.

### Is DBRX or DeepSeek-V3.1-Terminus better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 32.3 in the Noometry coding category.

### How many benchmarks do DBRX and DeepSeek-V3.1-Terminus share?

10 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.