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 3.1 Pro vs Gemini 3 Flash

Verdict

Gemini 3.1 Pro leads 15–0 across 15 shared benchmarks.

Gemini 3.1 Pro 15 · Gemini 3 Flash 0 · higher isn't always better — see caveats.

Per-benchmark head-to-head

Gemini 3.1 ProGemini 3 Flash
  • 33.5
    APEX-Agents
    24
  • 98
    ARC-AGI
    21.5
  • 77.1
    ARC-AGI-2
    33.61
  • 57
    Balrog
    48.1
  • 55
    Chess Puzzles
    38
  • 26.83
    FrontierMath-Tier-4-v2-Private
    17.07
  • 59.65
    FrontierMath-Tiers-1-3-v2-Private
    51.23
  • 92.13
    GPQA diamond
    77.61
  • 22.55
    GSO-Bench
    9.8
  • 95.6
    OTIS Mock AIME 2024-2025
    92.77
  • 75.52
    SimpleBench
    53.32
  • 77.3
    SimpleQA Verified
    67.4
  • 75.62
    SWE-Bench verified
    75.41
  • 80.2
    Terminal Bench
    64.3
  • 72.1
    WeirdML
    61.6
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

  • Gemini 3.1 Pro98
  • Gemini 3 Flash92.77

Gemini 3.1 Pro vs …

  • vs PowerMoE-3b
  • vs Claude Fable 5
  • vs GPT-5.5
  • vs Llama 3.1-405B
  • vs phi-3-small 7.4B