Model comparison

DBRX vs Gemini 3.7 Flash

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 29.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

DBRX Databricks

29.4

Rank #311 Confirmed

Gemini 3.7 Flash Google

59.8

Rank #14 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and Gemini 3.7 Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.7 Flash leads 69.7 to 14.9.
  • The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 94.8% for Gemini 3.7 Flash.
  • DBRX has downloadable open weights; the other is API-only.

Side by side

DBRX and Gemini 3.7 Flash specifications
DBRXGemini 3.7 Flash
ProviderDatabricksGoogle
Noometry Index29.459.8
Released2024-03-272026-08-13
WeightsOpenProprietary
Context window—1.05M
Max output—66K
Input $ / M tokens—$0.75
Output $ / M tokens—$3.75
Results tracked2144

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

Category by category

Coding Gemini 3.7 Flash leads

DBRX: 32.9 (#266), Gemini 3.7 Flash: 56.2 (#22)

Coding benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Coding11321497
DeepSWE—65.5%
FrontierCode—43.6%
LMArena WebDev—1592
FrontierSWE—20.3%
SciCode—59.8%
ALE-Bench—904.3
HumanEval+70.1%—
MBPP+55.8%—

Agentic & Tool Use Not comparable

DBRX: —, Gemini 3.7 Flash: 42.1 (#19)

Agentic & Tool Use benchmarks
BenchmarkDBRXGemini 3.7 Flash
APEX-Agents—67.8%
Remote Labor Index—5%
GDP.pdf—23.8%

Reasoning Gemini 3.7 Flash leads

DBRX: 21.4 (#222), Gemini 3.7 Flash: 70.0 (#15)

Reasoning benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Hard Prompts11131494
ARC-AGI-2—84.6%
NYT Connections (extended)—94%
ARC-AGI-1—95.5%
CritPt—14.3%
Chess Puzzles—47%
Mystery Game Puzzles—37%
DTBench—96.8%
LMCA—50.4%
Epoch Capabilities Index—157.27

Math Gemini 3.7 Flash leads

DBRX: 24.3 (#269), Gemini 3.7 Flash: 69.6 (#23)

Math benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Math11451507
FrontierMath (Tiers 1-3)—71.6%
FrontierMath Tier 4—36.6%
OTIS Mock AIME 2024-2025—97.2%
ProofBench—58%
MATH Level 511.7%—

Knowledge Gemini 3.7 Flash leads

DBRX: 14.9 (#294), Gemini 3.7 Flash: 69.7 (#5)

Knowledge benchmarks
BenchmarkDBRXGemini 3.7 Flash
GPQA Diamond32.9%94.8%
LMArena Expert10761508
SimpleQA Verified—69.2%

Multimodal Not comparable

DBRX: —, Gemini 3.7 Flash: 37.3 (#73)

Multimodal benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Vision—1316
Furniture Assembly—26.7%

Multilingual Gemini 3.7 Flash leads

DBRX: 29.3 (#268), Gemini 3.7 Flash: 57.6 (#7)

Multilingual benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Non-English10711484
LMArena Chinese10681548
LMArena French10961505
LMArena German10571498
LMArena Japanese9901512
LMArena Korean9931483
LMArena Russian10781516
LMArena Spanish10641503

Instruction Following Gemini 3.7 Flash leads

DBRX: 57.5 (#270), Gemini 3.7 Flash: 77.7 (#15)

Instruction Following benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Instruction Following11121483

Long Context Gemini 3.7 Flash leads

DBRX: 33.7 (#258), Gemini 3.7 Flash: 45.7 (#30)

Long Context benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Longer Query11121492

Writing & Preference Gemini 3.7 Flash leads

DBRX: 33.6 (#275), Gemini 3.7 Flash: 71.2 (#20)

Writing & Preference benchmarks
BenchmarkDBRXGemini 3.7 Flash
LMArena Text11191486
LMArena Creative Writing11041490
LMArena Multi-Turn11111489
EQ-Bench Creative Writing—1723

Frequently asked questions

Is DBRX better than Gemini 3.7 Flash?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 29.4 on the Noometry Index.

Is DBRX or Gemini 3.7 Flash better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 32.9 in the Noometry coding category.

How many benchmarks do DBRX and Gemini 3.7 Flash share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Gemini 3.7 Flash has 44.

Related comparisons

Go deeper