LLM Stats (AutomationBench; Protocol unverified — beam-1.0-501b-a23b): leaderboard
LLM Stats reports Beam 1.0 BF16 on the AutomationBench public split, citing the Reflection model card with temperature 0.7 and top-p 0.99. This source-qualified mirror is retained separately while exact protocol correspondence is unverified; score is task success percent.
Metric: Score (%). Source: llm-stats.com. 1 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Beam 1.0 | 39.3 | #86 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-automationbench-protocol-unverified-beam-1-0-501b-a23b · How It Works · Data refreshed daily, snapshot 2026-10-22.