One system explained to an engineer, a physicist and a VC, then somebody else's architecture debugged cold. Docs use the same muscle.
3 challenges20 models
20 models tested across 3 api documentation challenges.Composite score: 30% Rival Index, 20% task coverage, 20% challenge-scoped duel performance, 15% recency, 15% tier. Deduplicated by product line. GPT-6 Astra leads at 77.7/100. Drawn from Rival's open dataset of 21,000+ human preference votes.
Rival's Pick#26 Rival IndexOpenai flagship
Too close to callComposite scores combine task evidence, Rival Index, recency, and model tier. Rival’s Pick is a separate editorial recommendation. How ranking works