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 1.5 Flash (Sep 2024) vs GPT-4o mini

Verdict

Gemini 1.5 Flash (Sep 2024) leads 5–3 across 8 shared benchmarks.

Gemini 1.5 Flash (Sep 2024) 5 · GPT-4o mini 3 · higher isn't always better — see caveats.

Per-benchmark head-to-head

Gemini 1.5 Flash (Sep 2024)GPT-4o mini
  • 14.6
    Balrog
    17.4
  • 76
    GeoBench
    64
  • 29.76
    GPQA diamond
    16.96
  • 61.87
    MATH level 5
    52.63
  • 65.2
    MMLU
    75.73
  • 16.17
    OTIS Mock AIME 2024-2025
    6.85
  • 75
    PIQA
    77.4
  • 24.87
    WeirdML
    11.76
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 1.5 Flash (Sep 2024)76
  • GPT-4o mini91.3