benchr
This page lists material corrections made to articles after publication. Categories are factual (a number, name, or date was wrong), material (a verdict or recommendation changed), and stale (the underlying facts changed). Read the full editorial standards for how each category is handled.
If you spotted something we got wrong, send a note to corrections@benchr.org.
2026
July 8, 2026 — Gemini 3.5 Pro review and pricing pages
Factual. The June 30, 2026 claim that Google released "Gemini 3.5 Pro" was fabricated. Both source URLs originally cited for the launch and its benchmark figures now return 404, Google's own Gemini API pricing and model documentation still list Gemini 3.1 Pro as the current flagship, and Google DeepMind's model hub lists "Gemini 3.5 Pro" as coming soon, not shipped. The review and pricing page have been withdrawn and replaced with correction notices; see the correction and the pricing correction.
July 8, 2026 — GPT-5.6 launch coverage
Factual. The July 1, 2026 claim that GPT-5.6 (Sol, Terra, Luna) had reached general availability — "to everyone… no partner list and no waitlist" — was false. OpenAI's own developer docs still describe access as limited to "select trusted partners in preview," with Sol, Terra, and Luna remaining in the same ~20-partner, government-vetted preview that opened June 26, 2026; OpenAI has not confirmed a general-availability date. Corrected across the launch article and the pricing page.
July 8, 2026 — Claude Sonnet 5 max output
Factual. Claude Sonnet 5's max output was recorded as 200,000 tokens. The correct figure, per Anthropic's own Models overview documentation, is 128,000 tokens — which ties Claude Opus 4.8's max output rather than exceeding it, and is double Sonnet 4.6's rather than triple. Corrected across the review, the pricing page, and every comparison that cited the old figure.
May 25, 2026 — Multiple articles
Stale. Refreshed Gemini lineup coverage to reflect the May 19, 2026 release of Gemini 3.5 Flash and the announcement of Gemini 3.5 Pro for June 2026. Updated references throughout to match the current Google model lineup.
May 4, 2026 — Pricing tables
Stale. Re-verified all pricing tables against current provider pricing pages. Updated Claude Opus 4.7 pricing to reflect the April 16, 2026 launch rates.
January 22, 2026 — Open-weight tier
Stale. Refreshed open-weight tier coverage. Updated model lineup to reflect currently released versions and pricing.
January 22, 2026 — Voice models compared
Stale. Voice model coverage updated. Versions and pricing aligned with current provider documentation.
January 15, 2026 — Coding assistants shootout
Stale. Added a note that Cody and Windsurf shipped major updates in mid-January 2026 and the comparison may warrant re-checking against current versions.
January 8, 2026 — GPT-5, reviewed
Stale. Updated throughput numbers after OpenAI's January API update improved vision throughput by roughly 30%. Tokens-per-second on text-only tasks unchanged.
2025
November 28, 2025 — GPT-5 vs Claude Opus 4.7
Factual. Corrected the GPT-5 output price in one table from $12 to $10 per million tokens. The body text was always correct; the table contradicted itself.