Model comparison

DBRX vs Gemma 2 9B

DBRX is the stronger model overall, scoring 29.4 to 25.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

DBRX Databricks

29.4

Rank #311 Confirmed

Gemma 2 9B Google

25.9

Rank #341 Confirmed

Summary

  • They share 19 benchmarks with published results for both. DBRX scores higher in 5 categories and Gemma 2 9B in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where DBRX leads 24.3 to 9.9.
  • The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 21% for Gemma 2 9B.

Side by side

DBRX and Gemma 2 9B specifications
DBRXGemma 2 9B
ProviderDatabricksGoogle
Noometry Index29.425.9
Released2024-03-272024-06-24
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2135

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

Category by category

Coding DBRX leads

DBRX: 32.9 (#266), Gemma 2 9B: 29.4 (#304)

Coding benchmarks
BenchmarkDBRXGemma 2 9B
LMArena Coding11321173
BigCodeBench Instruct—34.7%
LiveBench Coding—22.5%
BigCodeBench Complete—40.6%
HumanEval+70.1%—
MBPP+55.8%—

Reasoning DBRX leads

DBRX: 21.4 (#222), Gemma 2 9B: 15.9 (#309)

Reasoning benchmarks
BenchmarkDBRXGemma 2 9B
LMArena Hard Prompts11131171
LiveBench Reasoning—15.2%
LiveBench Data Analysis—36.4%
Epoch Capabilities Index—119.83
LiveBench—28.7%
PIQA—83.7%

Math DBRX leads

DBRX: 24.3 (#269), Gemma 2 9B: 9.9 (#318)

Math benchmarks
BenchmarkDBRXGemma 2 9B
LMArena Math11451183
MATH Level 511.7%21%
OTIS Mock AIME 2024-2025—0.6%
LiveBench Math—19.8%
GSM8K—84.9%

Knowledge DBRX leads

DBRX: 14.9 (#294), Gemma 2 9B: 9.7 (#305)

Knowledge benchmarks
BenchmarkDBRXGemma 2 9B
GPQA Diamond32.9%27.5%
LMArena Expert10761147
BoolQ—85.7%
MMLU—72.1%

Multilingual Gemma 2 9B leads

DBRX: 29.3 (#268), Gemma 2 9B: 36.6 (#238)

Multilingual benchmarks
BenchmarkDBRXGemma 2 9B
LMArena Non-English10711188
LMArena Chinese10681185
LMArena French10961190
LMArena German10571186
LMArena Japanese9901144
LMArena Korean9931137
LMArena Russian10781200
LMArena Spanish10641200

Instruction Following Too close to call

DBRX: 57.5 (#270), Gemma 2 9B: 57.6 (#269)

Instruction Following benchmarks
BenchmarkDBRXGemma 2 9B
LMArena Instruction Following11121178
LiveBench Instruction Following—52.6%

Long Context Gemma 2 9B leads

DBRX: 33.7 (#258), Gemma 2 9B: 36.3 (#233)

Long Context benchmarks
BenchmarkDBRXGemma 2 9B
LMArena Longer Query11121197

Writing & Preference DBRX leads

DBRX: 33.6 (#275), Gemma 2 9B: 32.1 (#281)

Writing & Preference benchmarks
BenchmarkDBRXGemma 2 9B
LMArena Text11191207
LMArena Creative Writing11041206
LMArena Multi-Turn11111193
EQ-Bench Creative Writing—841
LiveBench Language—25.5%

Frequently asked questions

Is DBRX better than Gemma 2 9B?

DBRX is the stronger model overall, scoring 29.4 to 25.9 on the Noometry Index.

Is DBRX or Gemma 2 9B better for coding?

DBRX scores higher on coding benchmarks: 32.9 versus 29.4 in the Noometry coding category.

How many benchmarks do DBRX and Gemma 2 9B share?

19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Gemma 2 9B has 35.

Related comparisons

Go deeper