{"schema":"postcutoff/event@1","as_of":"2026-11-19T22:11:00+01:00","url":"https://postcutoff.com/e/2026-09-24-c5r-facility-0-sciuniverse-benchmark/","md":"https://postcutoff.com/e/2026-09-24-c5r-facility-0-sciuniverse-benchmark/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-24-c5r-facility-0-sciuniverse-benchmark","date":"2026-09-24","date_precision":"day","short_title":"C5R opens Facility-0, an AI-run wet lab, and the SciUniverse benchmark","deck":"Claude Fable 5.1 leads with 45.3%","takeaway":"On Sept 24, 2026 San Francisco startup C5R (founder Michael Akilian) launched Facility-0, a physical lab where frontier models plan experiments and run them by controlling instruments and instructing human operators.","category":"benchmark","category_label":"Benchmarks","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"C5R: SciUniverse benchmark and results","url":"https://c5r.net/sciuniverse/","type":"official","group":"primary","domain":"c5r.net"},{"n":2,"title":"C5R launch post on X","url":"https://x.com/c5rcorp/status/2103156979250417801","type":"official","group":"primary","domain":"x.com"},{"n":3,"title":"Runtime Wire: C5R is building physical labs for AI models that still struggle with experiments","url":"https://runtimewire.com/article/c5r-physical-lab-ai-models-michael-akilian","type":"press","group":"press","domain":"runtimewire.com"},{"n":4,"title":"Glitchwire: C5R built a research lab run by AI in 12 weeks","url":"https://glitchwire.com/news/c5r-built-a-research-lab-run-by-ai-in-12-weeks-the-sciuniverse-benchmark-shows-w/","type":"press","group":"press","domain":"glitchwire.com"},{"n":5,"title":"Michael Akilian launch thread","url":"https://x.com/akilian/status/2103158262111887542","type":"discussion","group":"reactions","domain":"x.com"},{"n":6,"title":"Import AI 475 (Jack Clark, Oct 5, 2026)","url":"https://importai.substack.com/p/import-ai-475-swarm-scaling-google","type":"discussion","group":"reactions","domain":"importai.substack.com"}],"official":2,"filed":"2026-10-05","updated":"2026-10-05","orgs":["C5R"],"title":"C5R opens Facility-0, an AI-run wet lab, and the SciUniverse benchmark: Claude Fable 5.1 leads with 45.3%","summary":"On Sept 24, 2026 San Francisco startup C5R (founder Michael Akilian) launched Facility-0, a physical lab where frontier models plan experiments and run them by controlling instruments and instructing human operators. It also launched SciUniverse Level 1, a benchmark of 92 tasks in 17 families across chemistry, biology and materials science, some done in the real lab and some in a digital twin. Claude Fable 5.1 scored 45.3% pass@1, ahead of GPT-6 Astra (32.5%) and Claude Opus 5 (30.5%). C5R says models \"repeatedly miss critical details in laboratory work\".","key_facts":["SciUniverse Level 1: 92 tasks, 17 task families (chemistry 7, biology 5, materials 4, cross-domain 1); tasks 'take no more than a few hours' for a scientist; family-weighted pass@1","Leaderboard (pass@1, model inference cost per task): Claude Fable 5.1 xhigh 45.3% ($40.61); GPT-6 Astra xhigh 32.5% ($52.37); Claude Opus 5 xhigh 30.5% ($46.31); Grok 4.6 xhigh 26.2% ($13.41); Gemini 3.8 Flash high 14.6% ($4.55); GPT-5.6 Sol xhigh 9.4% ($16.53)","Real-world tasks include synthesising and detecting an amide (N-benzyl-4-methylbenzamide) by LC–MS, cell-free sfGFP expression, PCR and DNA recovery, alpha-alumina synthesis and pressing BaTiO₃ pellets; simulated tasks include a two-week automated PCR lab with supply shortages and equipment failures","Failure modes named by C5R: pipetting frozen samples, contaminating DNA, ignoring evaporating solvents, vortexing open containers","Facility-0 was built in 12 weeks; press coverage reports more than 40 integrated instruments","Launch post on X: 787k views (account with about 3k followers) when checked Oct 5; covered in Import AI 475 (Oct 5)"],"key_numbers":[],"tags":["benchmark","ai-scientist","wet-lab","lab-automation","chemistry","biology","materials","claude-fable-5-1","gpt-6-astra"],"science":null,"body_md":"## What happened\n\nC5R says its goal is to give models a physical workspace: \"Getting AI to do useful scientific work requires a physical workspace connected\nto instruments and experiments, rather than another system that operates only on digital data\" (Akilian, per Runtime Wire). In Facility-0\nthe model drives a harness that operates machines (pipettes, LC–MS, X-ray, presses, a Hamilton liquid handler in simulation) and gives\ninstructions to human operators. The website shows recorded footage of GPT-6 Astra synthesising an amide.\n\nSciUniverse Level 1 is deliberately easy work for a trained scientist. The best model still fails more than half of it. C5R notes that\nreal-world tasks have few rollouts, so those scores are noisy.\n\n## Why it matters\n\nMost AI-for-science benchmarks test reasoning on text or data. This one tests whether a model's plan works with real reagents and\ninstruments, and the low scores show how far \"AI scientist\" claims are from autonomous wet-lab work. It is a new benchmark from a startup\nand has not been independently reproduced. Funding was not disclosed.","disputed":[],"related":[],"people":[{"id":"jack-clark","name":"Jack Clark","url":"https://postcutoff.com/person/jack-clark/"}],"posts":[{"id":"x-akilian-2103158262111887542","title":"“18 months ago, I went all in on studying biology. I started by building a lab in my…”","url":"https://postcutoff.com/p/x-akilian-2103158262111887542/"},{"id":"2026-09-24-c5rcorp-facility-0-sciuniverse","title":"C5R: 'In 12 weeks, we built a research facility that is run entirely by AI' (SciUniverse benchmark launch)","url":"https://postcutoff.com/p/2026-09-24-c5rcorp-facility-0-sciuniverse/"}],"videos":[],"models":[],"changes":[{"date":"2026-10-05","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-05","run":null,"sources_read":null,"updated":"2026-10-05","human_review":null,"version":{"date":"2026-10-06"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":116,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":86,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":177,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":116,"in_training_data":false}],"short_url":null}