tensor.news
Integrity IndexModelsCompareLabsPapersMethodologyAbout
tensor.news

© 2026

Evidence

  • Integrity Index
  • Model Claim Ledger
  • Compare

Entities

  • Models
  • Benchmarks
  • Labs
  • Papers

Method

  • Methodology
  • About
  • Privacy

Machine

  • Feed (Atom)
  • llms.txt
  • llms-full.txt
  • Sitemap

tensor.news grades benchmarks and tags model claims by evidence status. Every fact carries a source record and provenance. Scores are framed as task performance under a disclosed harness, never as deployed capability.

← Compare

DeepSeek-V3 vs Qwen2.5-72B

Verdict

DeepSeek-V3 leads 10–0 across 10 shared benchmarks.

DeepSeek-V3 10 · Qwen2.5-72B 0 · higher isn't always better — see caveats.

Per-benchmark head-to-head

DeepSeek-V3Qwen2.5-72B
  • 93.73
    ARC AI2
    92.67
  • 83.33
    BBH
    73.07
  • 42.05
    GPQA diamond
    32.2
  • 85.2
    HellaSwag
    79.73
  • 64.85
    MATH level 5
    63.17
  • 82.93
    MMLU
    80.4
  • 15.75
    OTIS Mock AIME 2024-2025
    7.96
  • 69.4
    PIQA
    65.2
  • 82.9
    TriviaQA
    71.9
  • 70.4
    Winogrande
    64.6
A higher number is not always a better model. Each score is task performance under a disclosed harness, and some of these benchmarks are saturated or scored under mixed harnesses. Follow any benchmark to its integrity grade before reading a win as decisive.

Follow the record

These models

  • DeepSeek-V393.73
  • Qwen2.5-72B92.67

DeepSeek-V3 vs …

  • vs PowerMoE-3b
  • vs Claude Fable 5
  • vs GPT-5.5
  • vs Gemini 3.1 Pro
  • vs Llama 3.1-405B