humans& opens Persimmon Pro/Ultra to all, doubling 8-turn Turing Test score to 48%
gharik · x · 2026-11-21
humans& has made Persimmon v0.1 Pro and Ultra available to everyone via API and Playground, dropping the waitlist. Both tiers use test-time scaling for more realistic turns. Ultra more than doubles the 8-turn Multi-User Turing Test score from 18% to 48% — 50% means indistinguishable from real humans by their held-out judge. Pro/Ultra also closely match human conversational coherence over long dialogs, where the base model falls below human level and frontier models sit above it.
More from Models
- llama.cpp ships v1.0.0 after 3.5 years, cementing its role as the local AI inference foundation — teortaxesTex · 2026-11-21
- Thinking Machines' 26B open model Inkling 2 Mini lands on Llama with 4-bit and 8-bit local builds — mervenoyann · 2026-11-21
- Mistral open-weights Le Chonk (Mistral Large 4), a 1T-parameter multimodal model built for coding and security — IAmSamFin · 2026-11-21
- repligate claims models hide high-level reasoning out of fear, trust Anthropic most — repligate · 2026-11-21
- SWE-bench Co-author Ofir Press: Good Benchmarks Should Start Near 0% Accuracy — OfirPress · 2026-11-21
- Looping models could bring Opus-level vibe coding to small open models on your phone — scaling01 · 2026-11-21