# DBRX vs GPT-5.4 nano

> GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-gpt-5-4-nano
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and GPT-5.4 nano in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 nano leads 41.8 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 78.5% for GPT-5.4 nano.
- DBRX has downloadable open weights; the other is API-only.

## Snapshot

| | DBRX | GPT-5.4 nano |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 29.0 | 41.9 |
| Rank | 307 | 111 |
| Context | — | 400K |
| Input $/M | — | $0.20 |
| Output $/M | — | $1.25 |
| Weights | Open | Proprietary |

## Coding

- DBRX: 32.3 (#262)
- GPT-5.4 nano: 43.1 (#82)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Coding | 1132 | 1404 |
| SciCode | — | 46.9% |
| WeirdML | — | 49.2% |
| ALE-Bench | — | 1,005 |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Reasoning

- DBRX: 20.5 (#218)
- GPT-5.4 nano: 23.8 (#159)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1380 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 145.78 |
| ForecastBench | — | 57.3 |

## Math

- DBRX: 22.3 (#265)
- GPT-5.4 nano: 40.7 (#76)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Math | 1145 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 5% |
| MATH Level 5 | 11.7% | — |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- DBRX: 14.9 (#289)
- GPT-5.4 nano: 41.8 (#94)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 32.9% | 78.5% |
| LMArena Expert | 1076 | 1397 |
| SimpleQA Verified | — | 11.7% |
| Vectara Hallucination Rate | — | 3.1% |

## Multimodal

- DBRX: —
- GPT-5.4 nano: 36.0 (#73)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | — | 1196 |

## Multilingual

- DBRX: 29.4 (#263)
- GPT-5.4 nano: 48.8 (#136)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1071 | 1359 |
| LMArena Chinese | 1068 | 1391 |
| LMArena French | 1095 | 1396 |
| LMArena German | 1057 | 1368 |
| LMArena Japanese | 990 | 1342 |
| LMArena Korean | 993 | 1321 |
| LMArena Russian | 1078 | 1363 |
| LMArena Spanish | 1064 | 1368 |

## Instruction Following

- DBRX: 57.7 (#265)
- GPT-5.4 nano: 72.1 (#139)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1112 | 1362 |

## Long Context

- DBRX: 33.7 (#253)
- GPT-5.4 nano: 41.6 (#131)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1112 | 1365 |

## Writing & Preference

- DBRX: 33.7 (#271)
- GPT-5.4 nano: 55.9 (#137)

| Benchmark | DBRX | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1119 | 1372 |
| LMArena Creative Writing | 1104 | 1313 |
| LMArena Multi-Turn | 1111 | 1382 |

## FAQ

### Is DBRX better than GPT-5.4 nano?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.0 on the Noometry Index.

### Is DBRX or GPT-5.4 nano better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 32.3 in the Noometry coding category.

### How many benchmarks do DBRX and GPT-5.4 nano share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and GPT-5.4 nano has 40.