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

GPT-5 vs Kimi K2 (Sep 2025)

Verdict

GPT-5 leads 3–1 across 4 shared benchmarks.

GPT-5 3 · Kimi K2 (Sep 2025) 1 · higher isn't always better — see caveats.

Per-benchmark head-to-head

GPT-5Kimi K2 (Sep 2025)
  • 88
    Aider polyglot
    59.1
  • 97.2
    Fiction.LiveBench
    66.7
  • 87.23
    Lech Mazur Writing
    87.29
  • 60.7
    WeirdML
    36.68
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

  • GPT-598.13
  • Kimi K2 (Sep 2025)87.29

Kimi K2 (Sep 2025) vs …

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