Noometry

Model comparison

DBRX vs Qwen3.5 397B-A17B

Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 29.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

DBRX Databricks

29.0

Rank #307 Confirmed

Qwen3.5 397B-A17B Alibaba (Qwen)

45.7

Rank #60 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DBRX scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 14.9.
  • The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 86.4% for Qwen3.5 397B-A17B.

Side by side

DBRXQwen3.5 397B-A17B
ProviderDatabricksAlibaba (Qwen)
Noometry Index29.045.7
Released2024-03-272026-02-01
WeightsOpenOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.60
Output $ / M tokens—$3.60
Results tracked2136

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

Category by category

Coding Qwen3.5 397B-A17B leads

DBRX: 32.3 (#262), Qwen3.5 397B-A17B: 41.7 (#108)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Coding11321464
LMArena WebDev—1400
HumanEval+70.1%—
MBPP+55.8%—

Agentic & Tool Use Not comparable

DBRX: —, Qwen3.5 397B-A17B: 33.2 (#51)

BenchmarkDBRXQwen3.5 397B-A17B
APEX-Agents—24.9%
τ²-bench Airline—81.5%
τ²-bench Banking—9.8%
τ²-bench Retail—84.4%
τ²-bench Telecom—97.8%

Reasoning Qwen3.5 397B-A17B leads

DBRX: 20.5 (#218), Qwen3.5 397B-A17B: 33.6 (#62)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Hard Prompts11131448
Kagi LLM Benchmark—73.7%
NYT Connections (extended)—58.9%
Chess Puzzles—13%
Thematic Generalization—65.1%
Mystery Game Puzzles—18%
DTBench—87.5%
LMCA—37.9%
Epoch Capabilities Index—146.64

Math Qwen3.5 397B-A17B leads

DBRX: 22.3 (#265), Qwen3.5 397B-A17B: 44.9 (#64)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Math11451455
FrontierMath (Tiers 1-3)—31.2%
OTIS Mock AIME 2024-2025—88.9%
MATH Level 511.7%—

Knowledge Qwen3.5 397B-A17B leads

DBRX: 14.9 (#289), Qwen3.5 397B-A17B: 53.3 (#53)

BenchmarkDBRXQwen3.5 397B-A17B
GPQA Diamond32.9%86.4%
LMArena Expert10761461

Multimodal Not comparable

DBRX: —, Qwen3.5 397B-A17B: 40.0 (#42)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Vision—1262

Multilingual Qwen3.5 397B-A17B leads

DBRX: 29.4 (#263), Qwen3.5 397B-A17B: 54.0 (#56)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Non-English10711431
LMArena Chinese10681501
LMArena French10951461
LMArena German10571447
LMArena Japanese9901427
LMArena Korean9931382
LMArena Russian10781429
LMArena Spanish10641443

Instruction Following Qwen3.5 397B-A17B leads

DBRX: 57.7 (#265), Qwen3.5 397B-A17B: 75.2 (#73)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Instruction Following11121424

Long Context Qwen3.5 397B-A17B leads

DBRX: 33.7 (#253), Qwen3.5 397B-A17B: 44.1 (#71)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Longer Query11121442

Writing & Preference Qwen3.5 397B-A17B leads

DBRX: 33.7 (#271), Qwen3.5 397B-A17B: 62.5 (#74)

BenchmarkDBRXQwen3.5 397B-A17B
LMArena Text11191438
LMArena Creative Writing11041401
LMArena Multi-Turn11111447
EQ-Bench Creative Writing—1478

Frequently asked questions

Is DBRX better than Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B is the stronger model overall, scoring 45.7 to 29.0 on the Noometry Index.

Is DBRX or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 41.7 versus 32.3 in the Noometry coding category.

How many benchmarks do DBRX and Qwen3.5 397B-A17B share?

18 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Qwen3.5 397B-A17B has 36.

Related comparisons

Go deeper