← All models
Compare

DeepSeek-V4-Pro-0813 vs Qwen 3.5 Flash (hosted 35B-A3B)

DeepSeek-V4-Pro-0813 (DeepSeek) and Qwen 3.5 Flash (hosted 35B-A3B) (Alibaba) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsQwen 3.5 Flash (hosted 35B-A3B)Alibaba
Scores
Intelligence (ECI)155144
Coding784
Math8813
Reasoning & Knowledge6918
Agentic & Tools
Specifications
DeveloperDeepSeekAlibaba
FamilyDeepSeekQwen
ReleasedAug 13, 2026Feb 25, 2026
Parameters1.6T
AvailabilityOpen weights (unrestricted)
Context window1M
Price — $/M input$0.58
Price — $/M output$1.74
Inputstext
Outputstext
Benchmarks
AIME 2024/202599%84%
ARC-AGI91%
ARC-AGI-261%
GPQA Diamond92%82%
Humanity's Last Exam41%
SciCode51%
SimpleQA Verified53%20%
WebDev Arena15821238
WeirdML66%
FrontierMath6%
FrontierMath Tier 40%

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Frequently asked questions

Is DeepSeek-V4-Pro-0813 better than Qwen 3.5 Flash (hosted 35B-A3B)?

On Epoch AI's Capabilities Index, DeepSeek-V4-Pro-0813 scores higher (155) than Qwen 3.5 Flash (hosted 35B-A3B) (144). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is better for coding, DeepSeek-V4-Pro-0813 or Qwen 3.5 Flash (hosted 35B-A3B)?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 78th vs 4th percentile among the models tracked on Model Beat.

Want a different match-up? Open the compare tool to add or swap models.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.