Model comparison

DBRX vs Phi-4 Mini

Phi-4 Mini is the stronger model overall, scoring 30.9 to 29.4 on the Noometry Index.

Last verified . 0 shared benchmarks.

DBRX Databricks

29.4

Rank #311 Confirmed

Phi-4 Mini Microsoft

30.9

Rank #283 Reported

Summary

  • The widest gap is in knowledge, where Phi-4 Mini leads 25.3 to 14.9.

Side by side

DBRX and Phi-4 Mini specifications
DBRXPhi-4 Mini
ProviderDatabricksMicrosoft
Noometry Index29.430.9
Released2024-03-272024-12-11
WeightsOpenOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.075
Output $ / M tokens—$0.30
Results tracked213

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

Category by category

Coding DBRX leads

DBRX: 32.9 (#266), Phi-4 Mini: 28.1 (#317)

Coding benchmarks
BenchmarkDBRXPhi-4 Mini
SciCode—10.8%
LMArena Coding1132—
HumanEval+70.1%—
MBPP+55.8%—

Reasoning Phi-4 Mini leads

DBRX: 21.4 (#222), Phi-4 Mini: 22.4 (#195)

Reasoning benchmarks
BenchmarkDBRXPhi-4 Mini
CritPt—0%
LMArena Hard Prompts1113—

Math Not comparable

DBRX: 24.3 (#269), Phi-4 Mini: —

Math benchmarks
BenchmarkDBRXPhi-4 Mini
LMArena Math1145—
MATH Level 511.7%—

Knowledge Phi-4 Mini leads

DBRX: 14.9 (#294), Phi-4 Mini: 25.3 (#262)

Knowledge benchmarks
BenchmarkDBRXPhi-4 Mini
GPQA Diamond32.9%—
Vectara Hallucination Rate—23.5%
LMArena Expert1076—

Multilingual Not comparable

DBRX: 29.3 (#268), Phi-4 Mini: —

Multilingual benchmarks
BenchmarkDBRXPhi-4 Mini
LMArena Non-English1071—
LMArena Chinese1068—
LMArena French1096—
LMArena German1057—
LMArena Japanese990—
LMArena Korean993—
LMArena Russian1078—
LMArena Spanish1064—

Instruction Following Not comparable

DBRX: 57.5 (#270), Phi-4 Mini: —

Instruction Following benchmarks
BenchmarkDBRXPhi-4 Mini
LMArena Instruction Following1112—

Long Context Not comparable

DBRX: 33.7 (#258), Phi-4 Mini: —

Long Context benchmarks
BenchmarkDBRXPhi-4 Mini
LMArena Longer Query1112—

Writing & Preference Not comparable

DBRX: 33.6 (#275), Phi-4 Mini: —

Writing & Preference benchmarks
BenchmarkDBRXPhi-4 Mini
LMArena Text1119—
LMArena Creative Writing1104—
LMArena Multi-Turn1111—

Frequently asked questions

Is DBRX better than Phi-4 Mini?

Phi-4 Mini is the stronger model overall, scoring 30.9 to 29.4 on the Noometry Index.

Is DBRX or Phi-4 Mini better for coding?

DBRX scores higher on coding benchmarks: 32.9 versus 28.1 in the Noometry coding category.

How many benchmarks do DBRX and Phi-4 Mini share?

0 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Phi-4 Mini has 3.

Related comparisons

Go deeper