Fermat's Last Theorem formalization: Fable 5.2 finishes in 30h, Opus 5.5 stalls at 26%
ivan_bezdomny · x · 2026-11-10
In a Lean formalization benchmark of Fermat's Last Theorem, Opus 5.5 with 1000 agents completed only 26% in 18 hours and barely progressed after 30 (27%), while Fable 5.2 finished the full formalization in 30 hours, already at 86% by hour 18. The author's takeaway: the model itself is the most important variable. Chart shows both completion curves.
Related event: 1,000 Fable 5.2 Agents Formalize Fermat's Last Theorem in 30 Hours(20 posts)→
More from coding & agent
- Tripwire Pilot publishes a public list of 542 GitHub bounty-spam accounts — damnGruz · 2026-11-10
- Vera launches gyms, benchmarks and agents for cloud infrastructure operations — tianyin_xu · 2026-11-10
- Illos.dev sells $69 agent skills that draw on-style SVG illustrations — sull · 2026-11-10
- Wisdom: an open-source local ledger for Claude Code and Codex agent sessions — Fit-Fail-3369 · 2026-11-10
- Claude Code deletes session transcripts after 30 days by default — one config line keeps them — Kyrannio · 2026-11-10
- Morph launches Ultra: unlimited Kimi and DeepSeek for $200/month — zack_overflow · 2026-11-10