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 Gemini 1.5 Pro (May 2024)

Verdict

DeepSeek-V3 leads 4–1 across 5 shared benchmarks.

DeepSeek-V3 4 · Gemini 1.5 Pro (May 2024) 1 · higher isn't always better — see caveats.

Per-benchmark head-to-head

DeepSeek-V3Gemini 1.5 Pro (May 2024)
  • 83.33
    BBH
    85.6
  • 42.05
    GPQA diamond
    27.82
  • 64.85
    MATH level 5
    40.75
  • 82.93
    MMLU
    81.2
  • 15.75
    OTIS Mock AIME 2024-2025
    6.71
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
  • Gemini 1.5 Pro (May 2024)85.6

DeepSeek-V3 vs …

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