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

Claude Opus 4.8 vs Gemini 3.5 Flash

Verdict

Claude Opus 4.8 leads 7–5 across 14 shared benchmarks.

Claude Opus 4.8 7 · Gemini 3.5 Flash 5 · 2 tied · higher isn't always better — see caveats.

Per-benchmark head-to-head

Claude Opus 4.8Gemini 3.5 Flash
  • 42.5
    APEX-Agents
    49.6
  • 92.5
    ARC-AGI
    92.5
  • 72.08
    ARC-AGI-2
    72.08
  • 34
    Chess Puzzles
    50
  • 20.86
    CritPt
    13.14
  • 63.8
    CursorBench
    49.8
  • 56.1
    FrontierMath-Tier-4-v2-Private
    26.83
  • 80
    FrontierMath-Tiers-1-3-v2-Private
    62.81
  • 70.9
    GBAEval
    6.7
  • 88.05
    GPQA diamond
    90.4
  • 98.33
    OTIS Mock AIME 2024-2025
    95.55
  • 57.76
    SimpleBench
    72.04
  • 39.5
    SimpleQA Verified
    68.4
  • 82.89
    WeirdML
    62.64
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

  • Claude Opus 4.898.33
  • Gemini 3.5 Flash95.55