Noometry

Model comparison

DBRX vs Qwen2.5 72B Instruct

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 29.0 on the Noometry Index.

Last verified . 19 shared benchmarks.

DBRX Databricks

29.0

Rank #307 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.5

Rank #259 Confirmed

Summary

  • They share 19 benchmarks with published results for both. DBRX scores higher in 1 category and Qwen2.5 72B Instruct in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.9 to 33.7.
  • The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 63.2% for Qwen2.5 72B Instruct.

Side by side

DBRXQwen2.5 72B Instruct
ProviderDatabricksAlibaba (Qwen)
Noometry Index29.031.5
Released2024-03-272024-09
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$1.40
Output $ / M tokens—$5.60
Results tracked2143

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

Category by category

Coding Too close to call

DBRX: 32.3 (#262), Qwen2.5 72B Instruct: 32.8 (#256)

BenchmarkDBRXQwen2.5 72B Instruct
LMArena Coding11321293
WeirdML—16%
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
HumanEval+70.1%—
MBPP+55.8%—

Agentic & Tool Use Not comparable

DBRX: —, Qwen2.5 72B Instruct: 22.0 (#124)

BenchmarkDBRXQwen2.5 72B Instruct
TheAgentCompany—5.7%
BALROG—16.2%
METR Time Horizons—35.8%

Reasoning Too close to call

DBRX: 20.5 (#218), Qwen2.5 72B Instruct: 21.4 (#197)

BenchmarkDBRXQwen2.5 72B Instruct
LMArena Hard Prompts11131271
DTBench—62.9%
LMCA—13.4%
BIG-Bench Hard—79.8%
Epoch Capabilities Index—129.01
ForecastBench—57.5
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math DBRX leads

DBRX: 22.3 (#265), Qwen2.5 72B Instruct: 18.1 (#281)

BenchmarkDBRXQwen2.5 72B Instruct
LMArena Math11451283
MATH Level 511.7%63.2%
OTIS Mock AIME 2024-2025—8.1%
Omni-MATH—33%

Knowledge Qwen2.5 72B Instruct leads

DBRX: 14.9 (#289), Qwen2.5 72B Instruct: 26.9 (#247)

BenchmarkDBRXQwen2.5 72B Instruct
GPQA Diamond32.9%49.1%
LMArena Expert10761245
MMLU-Pro—63.1%
Confabulations—19.1%
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multilingual Qwen2.5 72B Instruct leads

DBRX: 29.4 (#263), Qwen2.5 72B Instruct: 41.2 (#208)

BenchmarkDBRXQwen2.5 72B Instruct
LMArena Non-English10711252
LMArena Chinese10681272
LMArena French10951279
LMArena German10571234
LMArena Japanese9901180
LMArena Korean9931188
LMArena Russian10781264
LMArena Spanish10641255

Instruction Following Qwen2.5 72B Instruct leads

DBRX: 57.7 (#265), Qwen2.5 72B Instruct: 65.7 (#216)

BenchmarkDBRXQwen2.5 72B Instruct
LMArena Instruction Following11121254
IFEval—80.6%

Long Context Qwen2.5 72B Instruct leads

DBRX: 33.7 (#253), Qwen2.5 72B Instruct: 38.9 (#183)

BenchmarkDBRXQwen2.5 72B Instruct
LMArena Longer Query11121282

Writing & Preference Qwen2.5 72B Instruct leads

DBRX: 33.7 (#271), Qwen2.5 72B Instruct: 46.9 (#210)

BenchmarkDBRXQwen2.5 72B Instruct
LMArena Text11191269
LMArena Creative Writing11041221
LMArena Multi-Turn11111272
WildBench—80.2%

Frequently asked questions

Is DBRX better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 29.0 on the Noometry Index.

Is DBRX or Qwen2.5 72B Instruct better for coding?

They score almost the same on coding (32.3 vs 32.8); test both on your own repository before choosing.

How many benchmarks do DBRX and Qwen2.5 72B Instruct share?

19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper