Model comparison

DBRX vs Granite 4.1 8b

Granite 4.1 8b is the stronger model overall, scoring 36.8 to 29.0 on the Noometry Index.

Last verified . 12 shared benchmarks.

DBRX Databricks

29.0

Rank #307 Confirmed

Granite 4.1 8b IBM

36.8

Rank #202 Confirmed

Summary

  • They share 12 benchmarks with published results for both. DBRX scores higher in 1 category and Granite 4.1 8b in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Granite 4.1 8b leads 35.5 to 14.9.

Side by side

DBRX and Granite 4.1 8b specifications
DBRXGranite 4.1 8b
ProviderDatabricksIBM
Noometry Index29.036.8
Released2024-03-27—
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2113

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

Category by category

Coding DBRX leads

DBRX: 32.3 (#262), Granite 4.1 8b: 29.9 (#291)

Coding benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Coding11321313
LMArena WebDev—1190
HumanEval+70.1%—
MBPP+55.8%—

Reasoning Granite 4.1 8b leads

DBRX: 20.5 (#218), Granite 4.1 8b: 24.6 (#142)

Reasoning benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Hard Prompts11131294

Math Granite 4.1 8b leads

DBRX: 22.3 (#265), Granite 4.1 8b: 33.8 (#167)

Math benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Math11451311
MATH Level 511.7%—

Knowledge Granite 4.1 8b leads

DBRX: 14.9 (#289), Granite 4.1 8b: 35.5 (#171)

Knowledge benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Expert10761310
GPQA Diamond32.9%—

Multilingual Granite 4.1 8b leads

DBRX: 29.4 (#263), Granite 4.1 8b: 41.8 (#199)

Multilingual benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Non-English10711261
LMArena Chinese10681335
LMArena Russian10781238
LMArena French1095—
LMArena German1057—
LMArena Japanese990—
LMArena Korean993—
LMArena Spanish1064—

Instruction Following Granite 4.1 8b leads

DBRX: 57.7 (#265), Granite 4.1 8b: 67.0 (#198)

Instruction Following benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Instruction Following11121268

Long Context Granite 4.1 8b leads

DBRX: 33.7 (#253), Granite 4.1 8b: 38.7 (#188)

Long Context benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Longer Query11121275

Writing & Preference Granite 4.1 8b leads

DBRX: 33.7 (#271), Granite 4.1 8b: 48.3 (#199)

Writing & Preference benchmarks
BenchmarkDBRXGranite 4.1 8b
LMArena Text11191291
LMArena Creative Writing11041249
LMArena Multi-Turn11111269

Frequently asked questions

Is DBRX better than Granite 4.1 8b?

Granite 4.1 8b is the stronger model overall, scoring 36.8 to 29.0 on the Noometry Index.

Is DBRX or Granite 4.1 8b better for coding?

DBRX scores higher on coding benchmarks: 32.3 versus 29.9 in the Noometry coding category.

How many benchmarks do DBRX and Granite 4.1 8b share?

12 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Granite 4.1 8b has 13.

Related comparisons

Go deeper