LoomBench (area fixed; Typed Decisions) - Attainment: leaderboard
Fraction of 11 instructed agents meeting their objective, in percent; Five agents, fixed areas; identical 11 match designs, 26 rounds, 100-unit loom; higher is better. Interfaces are separate and random controls omitted.
Metric: Fraction of 11 instructed agents meeting their objective, in percent; Five agents, fixed areas; identical 11 match designs, 26 rounds, 100-unit loom; higher is better. Interfaces are separate and random controls omitted.. Source: raw.githubusercontent.com. Saturation forecast: Around January 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Luna | 100 | #52 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=loombench-area-fixed-typed-decisions-attainment · How It Works · Data refreshed daily, snapshot 2026-10-16.