Archive - Dataset News

Refreshing general-knowledge benchmarks without leakage

Static QA tests are showing their age; how to refresh without rewarding recollection.

Aug 21, 2025 • Michael Gordon

Leaderboards move when the judge changes. Here’s how to keep web-agent evaluations stable enough to buy, benchmark, and ship against.

Aug 14, 2025 • Michael Gordon

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts