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-Max

Qwen·released 2025-09-05

independently reproduced

Scored on 9 benchmarks. 56% of its scores are independently reproduced — the rest are self-reported or unverified.

9
Benchmarks scored
0
SOTA leads
97.13
Best score
56%
Reproduced
5 of 9

Benchmark fingerprint

Every score, ranked, colored by evidence status.

  • MATH level 5
    97.13
  • Lech Mazur Writing
    87.11
  • OTIS Mock AIME 2024-2025
    73.31
  • SimpleQA Verified
    67.47
  • Fiction.LiveBench
    66.7
  • GPQA diamond
    63.47
  • CL-bench
    14.5
  • PostTrainBench
    7.42
  • Chess Puzzles
    4

All benchmark scores

BenchmarkScoreEvidence statusMeasured
MATH level 597.13accuracy (%)reproduced· optimized2025-09-05
Lech Mazur Writing87.11accuracy (%)unverified2025-09-05
OTIS Mock AIME 2024-202573.31accuracy (%)reproduced· optimized2025-09-05
SimpleQA Verified67.47accuracy (%)reproduced2025-09-05
Fiction.LiveBench66.7accuracy (%)unverified2025-09-05
GPQA diamond63.47accuracy (%)reproduced· optimized2025-09-05
CL-bench14.5accuracy (%)unverified2025-09-05
PostTrainBench7.42accuracy (%)unverified2025-09-05
Chess Puzzles4accuracy (%)reproduced2025-09-05
9 source records · epoch_benchmarks. Every score is evidence-linked.

Follow the record

More from Qwen

  • 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
  • Qwen2.5-Coder-14B88.7