LLM Stats (AA-Briefcase v1.1): leaderboard

Artificial Analysis Briefcase v1.1 evaluates agents on multi-hour professional office work over real files. LLM Stats mirrors the reported quality Elo, higher is better; this version and scale stay separate from unversioned rubric pass rates.

Metric: Score. Source: llm-stats.com. 8 models tracked. Updated 21 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 5.51822#9
2Claude Sonnet 5.51811#24
3Claude Fable 5.21785#2
4Kimi K3.1 Pro1678#35
5Grok 4.71657#55
6Claude Haiku 5.51578#75
7Inkling 2 Mini1263#188
8Solar Mini 4872#529

Interactive version: theaggregate.ai/benchmark?slug=llm-stats-aa-briefcase-v1-1 · How It Works · Data refreshed daily, snapshot 2026-11-22.