all the models — AI benchmark observatory
← Benchmarks

AA-Briefcase

AA-Briefcase is an Artificial Analysis evaluation of AI systems on professional knowledge-work tasks, reported as an Elo score.

id aa-briefcase · max 3000 · 3 models reported

#ModelScore
1Grok 4.6
xAI
1577.00
2Kimi K3
Moonshot AI · open
1548.00
3Inkling-Small
Thinking Machines Lab · open
917.00