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

Gemini 2.5 Pro (Mar 2025) vs o3

Verdict

o3 leads 9–2 across 11 shared benchmarks.

Gemini 2.5 Pro (Mar 2025) 2 · o3 9 · higher isn't always better — see caveats.

Per-benchmark head-to-head

Gemini 2.5 Pro (Mar 2025)o3
  • 72.9
    Aider polyglot
    81.3
  • 33
    ARC-AGI
    60.8
  • 64
    CadEval
    74
  • 66.7
    Fiction.LiveBench
    88.9
  • 81
    GeoBench
    74
  • 78.45
    GPQA diamond
    75.76
  • 14.03
    HLE
    16.3
  • 80.5
    Lech Mazur Writing
    83.9
  • 95.56
    MATH level 5
    97.77
  • 41.92
    SimpleBench
    43.72
  • 22
    VPCT
    28
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

  • Gemini 2.5 Pro (Mar 2025)95.56
  • o397.77