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

OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (Hermes (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 December 2027. 14 models tracked. Updated 22 Nov 2026.

Top models

#ModelScoreOverall rank
1GLM-5.257.9#154
2Kimi K355#62
3Claude Sonnet 554.5#124
4Claude Opus 4.754#86
5DeepSeek V4 Pro53.8#201
6Claude Opus 4.853.6#64
7DeepSeek V4 Flash52.4#273
8GLM-5.151#200
9GPT-5.550#56
10Qwen 3.6 Max48.6#192
11Qwen 3.7 Plus47.4#221
12Kimi K2.646.9#197
13Qwen 3.7 Max45.2#160
14Qwen 3.6 Plus42.1#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-hermes-search-strict-success · How It Works · Data refreshed daily, snapshot 2026-11-22.