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

GPT-4.1 nano

OpenAI·released 2025-04-14

independently reproduced

Scored on 10 benchmarks. 40% of its scores are independently reproduced — the rest are self-reported or unverified.

10
Benchmarks scored
0
SOTA leads
70
Best score
40%
Reproduced
4 of 10

Benchmark fingerprint

Every score, ranked, colored by evidence status.

  • MATH level 5
    70
  • GPQA diamond
    31.9
  • OTIS Mock AIME 2024-2025
    28.82
  • Fiction.LiveBench
    25
  • WeirdML
    18.98
  • Aider polyglot
    8.9
  • FrontierMath-2025-02-28-Private
    1.81
  • CritPt
    0
  • ARC-AGI
    0
  • ARC-AGI-2
    0

All benchmark scores

BenchmarkScoreEvidence statusMeasured
MATH level 570accuracy (%)reproduced· optimized2025-04-14
GPQA diamond31.9accuracy (%)reproduced· optimized2025-04-14
OTIS Mock AIME 2024-202528.82accuracy (%)reproduced· optimized2025-04-14
Fiction.LiveBench25accuracy (%)unverified2025-04-14
WeirdML18.98accuracy (%)unverified2025-04-14
Aider polyglot8.9accuracy (%)unverified· optimized2025-04-14
FrontierMath-2025-02-28-Private1.81accuracy (%)reproduced· optimized2025-04-14
CritPt0accuracy (%)unverified2025-04-14
ARC-AGI0accuracy (%)unverified· optimized2025-04-14
ARC-AGI-20accuracy (%)unverified2025-04-14
10 source records · epoch_benchmarks. Every score is evidence-linked.

Follow the record

More from OpenAI

  • GPT-5.5100
  • GPT-5.5 Pro100
  • GPT-598.13
  • GPT-5 mini97.85
  • o4-mini97.83
  • o397.77