Which AI model scores highest on AA-Briefcase?

Claude Fable 5.1 by Anthropic holds the best AA-Briefcase result among tracked models, at 1694 (released Sep 1 2026). Higher scores are better on this benchmark.

What are the top 4 models on AA-Briefcase?

1. Claude Fable 5.1 (Anthropic) — 1694; 2. Claude Opus 5 (Anthropic) — 1685; 3. Grok 4.6 (SpaceXAI) — 1577; 4. Grok 4.5 (SpaceXAI) — 1313.

How many models have a published AA-Briefcase score?

4 tracked models have a published AA-Briefcase score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.

Knowledge work

AA-Briefcase

Artificial Analysis agentic office-work eval (Elo)

Rankings

Higher is better

AA-Briefcase — frequently asked questions

: Artificial Analysis agentic office-work eval (Elo)
: Claude Fable 5.1 by Anthropic holds the best AA-Briefcase result among tracked models, at 1694 (released Sep 1 2026). Higher scores are better on this benchmark.
: 1. Claude Fable 5.1 (Anthropic) — 1694; 2. Claude Opus 5 (Anthropic) — 1685; 3. Grok 4.6 (SpaceXAI) — 1577; 4. Grok 4.5 (SpaceXAI) — 1313.
: 4 tracked models have a published AA-Briefcase score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.