OfficePrism-420 - DeepAgents (Search) - Strict Success: leaderboard

OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (DeepAgents (Search) - Strict Success) across 420 tasks in 7 business functions.

Metric: Strict Success Rate (%) over 420 single-domain enterprise tasks. Source: arxiv.org. Saturation forecast: Around June 2027. 14 models tracked. Updated 22 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 558.6#124
2GPT-5.557.6#56
3Kimi K357.4#62
4GLM-5.255.7#154
5Claude Opus 4.755.5#86
6Claude Opus 4.855.5#64
7GLM-5.154.8#200
8Qwen 3.7 Max54#160
9Qwen 3.7 Plus53.8#221
10DeepSeek V4 Pro53.1#201
11Kimi K2.651.2#197
12DeepSeek V4 Flash50.7#273
13Qwen 3.6 Max50.5#192
14Qwen 3.6 Plus45.5#245

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=officeprism-420-deepagents-search-strict-success · How It Works · Data refreshed daily, snapshot 2026-11-22.