Model comparison

DBRX vs Wizardlm 13b

Wizardlm 13b is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.

Last verified . 10 shared benchmarks.

DBRX Databricks

29.4

Rank #311 Confirmed

Wizardlm 13b Microsoft

31.4

Rank #274 Confirmed

Summary

  • They share 10 benchmarks with published results for both. DBRX scores higher in 6 categories and Wizardlm 13b in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Wizardlm 13b leads 30.2 to 24.3.

Side by side

DBRX and Wizardlm 13b specifications
DBRXWizardlm 13b
ProviderDatabricksMicrosoft
Noometry Index29.431.4
Released2024-03-27—
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2110

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

Category by category

Coding DBRX leads

DBRX: 32.9 (#266), Wizardlm 13b: 30.1 (#298)

Coding benchmarks
BenchmarkDBRXWizardlm 13b
LMArena Coding11321035
HumanEval+70.1%—
MBPP+55.8%—

Reasoning DBRX leads

DBRX: 21.4 (#222), Wizardlm 13b: 19.4 (#259)

Reasoning benchmarks
BenchmarkDBRXWizardlm 13b
LMArena Hard Prompts11131018

Math Wizardlm 13b leads

DBRX: 24.3 (#269), Wizardlm 13b: 30.2 (#238)

Math benchmarks
BenchmarkDBRXWizardlm 13b
LMArena Math11451017
MATH Level 511.7%—

Knowledge Not comparable

DBRX: 14.9 (#294), Wizardlm 13b: —

Knowledge benchmarks
BenchmarkDBRXWizardlm 13b
GPQA Diamond32.9%—
LMArena Expert1076—

Multilingual DBRX leads

DBRX: 29.3 (#268), Wizardlm 13b: 27.1 (#277)

Multilingual benchmarks
BenchmarkDBRXWizardlm 13b
LMArena Non-English10711034
LMArena Chinese10681023
LMArena French1096—
LMArena German1057—
LMArena Japanese990—
LMArena Korean993—
LMArena Russian1078—
LMArena Spanish1064—

Instruction Following DBRX leads

DBRX: 57.5 (#270), Wizardlm 13b: 53.5 (#285)

Instruction Following benchmarks
BenchmarkDBRXWizardlm 13b
LMArena Instruction Following11121048

Long Context DBRX leads

DBRX: 33.7 (#258), Wizardlm 13b: 32.0 (#273)

Long Context benchmarks
BenchmarkDBRXWizardlm 13b
LMArena Longer Query11121054

Writing & Preference DBRX leads

DBRX: 33.6 (#275), Wizardlm 13b: 30.5 (#287)

Writing & Preference benchmarks
BenchmarkDBRXWizardlm 13b
LMArena Text11191077
LMArena Creative Writing11041091
LMArena Multi-Turn11111047

Frequently asked questions

Is DBRX better than Wizardlm 13b?

Wizardlm 13b is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.

Is DBRX or Wizardlm 13b better for coding?

DBRX scores higher on coding benchmarks: 32.9 versus 30.1 in the Noometry coding category.

How many benchmarks do DBRX and Wizardlm 13b share?

10 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Wizardlm 13b has 10.

Related comparisons

Go deeper