Claude Code · Anthropic · Claude · GitHub
Livenerf: Has Opus 5.5 been nerfed yet?
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
The 2025 quality incidents turned out to be infrastructure bugs, not deliberate downgrades.
Key facts
- Claude Opus 5.5 came out on 2026-09-22, so this is a chance to start the clock on launch day and keep it running
- Day 1 was 2026-09-24 22:10 UTC, about 2.5 days after launch
- All 6 days ran the full 90 samples on the same harness hash ( 461391b6fce64167 ) and pinned CLI (2.1.280)
- Progress (2026-09-29): 6 of 30 days collected (baseline 6 of 10), none missed
Summary
Along-running, deterministic-as-possible benchmark for detecting whether a frontier model gets quietly worse after launch. Livenerf is a small, boring, append-only benchmark for one question: does a model get worse after it ships? Claude Opus 5.5 came out on 2026-09-22, so this is a chance to start the clock on launch day and keep it running. Right now v0 runs on a Claude Max subscription through headless Claude Code ( claude-p ), with no API key. It's built on Inspect, the UK AI Security Institute's open-source eval framework. For questions about the repo, open a thread in the Discussions tab or an issue. The series is running. It runs once a day for 30 days: days 1–10 are the baseline, then there are two 10-day windows, so the first possible call is around 2026-10-24. Progress (2026-09-29): 6 of 30 days collected (baseline 6 of 10), none missed.