Noometry

Model comparison

DBRX vs GPT-5.4

GPT-5.4 is the stronger model overall, scoring 59.4 to 29.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

DBRX Databricks

29.4

Rank #311 Confirmed

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and GPT-5.4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 leads 65.3 to 14.9.
  • The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 93.3% for GPT-5.4.
  • DBRX has downloadable open weights; the other is API-only.

Side by side

DBRXGPT-5.4
ProviderDatabricksOpenAI
Noometry Index29.459.4
Released2024-03-272026-03-05
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2.50
Output $ / M tokens—$15
Results tracked2168

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-5.4 leads

DBRX: 32.9 (#266), GPT-5.4: 52.6 (#33)

BenchmarkDBRXGPT-5.4
LMArena Coding11321497
SWE-bench Verified—76.9%
DeepSWE—51.8%
LMArena WebDev—1465
SciCode—56.6%
GSO—31.4%
WeirdML—77.7%
MirrorCode—15.6%
ALE-Bench—1,607
AlgoTune—1.85
HumanEval+70.1%—
MBPP+55.8%—

Agentic & Tool Use Not comparable

DBRX: —, GPT-5.4: 46.5 (#13)

BenchmarkDBRXGPT-5.4
Terminal-Bench—81.8%
APEX-Agents—52.4%
τ²-bench Banking—39.4%
DeepResearch Bench—35.1%
PostTrainBench—19%
GBAEval—45.1%
LMArena Search—1197
METR Time Horizons—74.3%
Vending-Bench 2—6,144

Reasoning GPT-5.4 leads

DBRX: 21.4 (#222), GPT-5.4: 61.8 (#19)

BenchmarkDBRXGPT-5.4
LMArena Hard Prompts11131485
ARC-AGI-2—74%
Kagi LLM Benchmark—63.8%
NYT Connections (extended)—91.3%
ARC-AGI-1—93.7%
CritPt—23.4%
Chess Puzzles—44%
EnigmaEval—16%
Thematic Generalization—80%
EBR-Bench—25.4%
Mystery Game Puzzles—37%
DTBench—94.4%
LMCA—52%
Epoch Capabilities Index—156.81
ForecastBench—59.5

Math GPT-5.4 leads

DBRX: 24.3 (#269), GPT-5.4: 73.5 (#19)

BenchmarkDBRXGPT-5.4
LMArena Math11451488
FrontierMath (Tiers 1-3)—78.6%
FrontierMath Tier 4—49%
MathArena Final-Answer Competitions—83.1%
OTIS Mock AIME 2024-2025—97.8%
ProofBench—56%
MATH Level 511.7%—
FrontierMath (Feb 2025 set)—47.6%
FrontierMath Tier 4 (v1)—27.1%

Knowledge GPT-5.4 leads

DBRX: 14.9 (#294), GPT-5.4: 65.3 (#14)

BenchmarkDBRXGPT-5.4
GPQA Diamond32.9%93.3%
LMArena Expert10761507
Humanity's Last Exam—36.2%
SimpleQA Verified—45.1%
Vectara Hallucination Rate—7%

Multimodal Not comparable

DBRX: —, GPT-5.4: 43.7 (#20)

BenchmarkDBRXGPT-5.4
LMArena Vision—1303
Blueprint-Bench 2—27.1%
Furniture Assembly—37.5%
LMArena Document—1471

Multilingual GPT-5.4 leads

DBRX: 29.3 (#268), GPT-5.4: 56.2 (#23)

BenchmarkDBRXGPT-5.4
LMArena Non-English10711465
LMArena Chinese10681519
LMArena French10961493
LMArena German10571472
LMArena Japanese9901485
LMArena Korean9931448
LMArena Russian10781480
LMArena Spanish10641454

Instruction Following GPT-5.4 leads

DBRX: 57.5 (#270), GPT-5.4: 77.1 (#27)

BenchmarkDBRXGPT-5.4
LMArena Instruction Following11121469

Long Context GPT-5.4 leads

DBRX: 33.7 (#258), GPT-5.4: 50.3 (#8)

BenchmarkDBRXGPT-5.4
LMArena Longer Query11121473
CL-bench—27.9%
CL-bench Life—21.7%

Writing & Preference GPT-5.4 leads

DBRX: 33.6 (#275), GPT-5.4: 71.9 (#17)

BenchmarkDBRXGPT-5.4
LMArena Text11191469
LMArena Creative Writing11041439
LMArena Multi-Turn11111482
EQ-Bench Creative Writing—1840
EQ-Bench 4—1272

Frequently asked questions

Is DBRX better than GPT-5.4?

GPT-5.4 is the stronger model overall, scoring 59.4 to 29.4 on the Noometry Index.

Is DBRX or GPT-5.4 better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.6 versus 32.9 in the Noometry coding category.

How many benchmarks do DBRX and GPT-5.4 share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and GPT-5.4 has 68.

Related comparisons

Go deeper