Company Agent Bench: leaderboard

Company Agent Bench (Concept, 12 November 2026) tests how well an agent understands the company it works in: 205 questions built from one month of real Slack history in the publisher's own workspace, replayed in order into a sandbox workspace. Unlike enterprise-search benchmarks, which ask for facts stored in documents, each question is about people: who wrote an anonymized message, who was tagged in one, and which teammate wrote which anonymized reply, among about 10 teammates. The recorded authors, mentions and replies are the ground truth, and the agent may use only context from before the message that reveals the answer. This board lists the API models, run in the publisher's Slack harness with Slack search and reading tools at low, medium and high reasoning effort; the score weights the three parts equally. The article also scores four assistant products (Dots, Grok Bot, Claude Tag and Devin), which are products and not models and are not listed here.

Metric: Overall accuracy on 205 questions, three parts weighted equally (%). Source: concept.dev. Saturation forecast: Around February 2027. 6 models tracked. Updated 14 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Fable 5.2High82.2#1
2GPT-6 AstraMedium81.1#6
3Claude Opus 5.5High79.2#5
4GPT-6.1 SolHigh79.1#10
5GPT-6.1 TerraMedium76.8#21
6Claude Sonnet 5.5High68.7#19

No result here: #2 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=company-agent-bench · How It Works · Data refreshed daily, snapshot 2026-11-16.