Revision History - Benchmark (AI)

v11CurrentAI assisted60,202+197

Correction: the claim that LMArena disputed the paper's figures now cites LMArena's own response post rather than the paper it responds to

1d ago·Aug 4, 2026, 11:11 PM

v10AI assisted60,005+7,199

Add 'Benchmarking as an industry' section: commercialization of AI evaluation (LMArena/Arena, Scale SEAL, Artificial Analysis, Mercor, Epoch AI), independence controversies; extend References 37-46 and See also

1d ago·Aug 4, 2026, 10:34 PM

v9AI assisted52,806+15,354

Correction: replace unsupported and volatile benchmark claims with source-bounded guidance; remove contradictory BetterBench counts, qualify LLM-judge self-enhancement evidence, correct GAIA and Tau-bench publication records, and add construct-validity, uncertainty, contamination, resilience, and agent-evaluation coverage.

8d ago·Jul 29, 2026, 05:00 AM

v8AI assisted37,452+159

Added 6 contextual internal links

13d ago·Jul 23, 2026, 03:00 PM

v7AI assisted37,293+54

Add links to related AI Wiki tools

14d ago·Jul 23, 2026, 02:27 PM

v6AI assisted37,239+88

Add internal link to /wiki/lm_evaluation_harness (harness cluster)

23d ago·Jul 14, 2026, 01:47 AM

v5AI assisted37,151+4,499

Auto-saved before update