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

Qwen3-235B-A22B-Instruct (Jul 2025)

Qwen·released 2025-07-25

unverified

Scored on 5 benchmarks. 0% of its scores are independently reproduced — the rest are self-reported or unverified.

5
Benchmarks scored
0
SOTA leads
59.6
Best score
0%
Reproduced
0 of 5

Benchmark fingerprint

Every score, ranked, colored by evidence status.

  • Aider polyglot
    59.6
  • Fiction.LiveBench
    52.9
  • WeirdML
    38.7
  • ARC-AGI
    11
  • ARC-AGI-2
    1.25

All benchmark scores

BenchmarkScoreEvidence statusMeasured
Aider polyglot59.6accuracy (%)unverified· optimized2025-07-25
Fiction.LiveBench52.9accuracy (%)unverified2025-07-25
WeirdML38.7accuracy (%)unverified2025-07-25
ARC-AGI11accuracy (%)unverified· optimized2025-07-25
ARC-AGI-21.25accuracy (%)unverified2025-07-25
5 source records · epoch_benchmarks. Every score is evidence-linked.

Follow the record

More from Qwen

  • Qwen3-Max97.13
  • Qwen3.7-Max94.99
  • Qwen2.5-72B92.67
  • Qwen 3.6 Max (Preview)91.1
  • Qwen2.5-Coder-32B91.1
  • Qwen 3.6 Plus90.55