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.

← Models

Grok 4.20

xAI·released 2026-02-17

unverified

Scored on 6 benchmarks. 0% of its scores are independently reproduced — the rest are self-reported or unverified.

6
Benchmarks scored
0
SOTA leads
89.5
Best score
0%
Reproduced
0 of 6

Benchmark fingerprint

Every score, ranked, colored by evidence status.

  • ARC-AGI
    89.5
  • ARC-AGI-2
    65.14
  • Terminal Bench
    57.3
  • WeirdML
    52.26
  • CL-bench
    22.2
  • CL-bench Life
    11.9

All benchmark scores

BenchmarkScoreEvidence statusMeasured
ARC-AGI89.5accuracy (%)unverified· optimized2026-02-17
ARC-AGI-265.14accuracy (%)unverified2026-02-17
Terminal Bench57.3accuracy (%)unverified· optimized2026-02-17
WeirdML52.26accuracy (%)unverified2026-02-17
CL-bench22.2accuracy (%)unverified2026-02-17
CL-bench Life11.9accuracy (%)unverified2026-02-17
6 source records · epoch_benchmarks. Every score is evidence-linked.

Follow the record

More from xAI

  • Grok 494.4
  • Grok 4 Fast94.4
  • Grok 4.3 Beta93.33
  • Grok-3 mini90.94
  • Grok 388.75
  • Grok-2 (Dec 2024)63.6