METR's AI time-horizon chart hasn't updated since May, leaving frontier model gains unmeasured
haider1 · x · 2026-10-12
METR's time-horizon chart, which measures how long a software task an LLM can complete with 80% success, hasn't added a new model since May 8. The author wonders how far recent frontier models could push the horizon and hopes METR resumes evaluations. The chart's latest entry is Claude Mythos Preview (early) at over 3 hours, ahead of Gemini 3.1 Pro and GPT-5.2 (high).
More from Models
- Claude Pro poll: 211,770 votes split on keeping 5h limits for 2X weekly usage — koltregaskes · 2026-10-12
- Byteification retrofits token-based LLMs to work at byte level, fixing letter-counting failures — PontiEdoardo · 2026-10-12
- Same Model, Different Harness: OpenCode Refuses Far More Than Codex in Side-by-Side Tests — Current_Balance6692 · 2026-10-12
- User claims GPT's $20 tier may be gone, pricing change suspected — sujingshen · 2026-10-12
- AWS open-sources Strands Decider 2B, a laptop-runnable decision model with no text generation — dl_weekly · 2026-10-12
- Sonnet 5.5 High vs Opus 5.5 Low: task-level cost data to pick your coding model — Headfirst-Into-Ditch · 2026-10-12