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

OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (OpenClaw (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: Not forecast. 14 models tracked. Updated 22 Nov 2026.

Top models

#ModelScoreOverall rank
1Kimi K357.1#62
2GLM-5.256.2#154
3Qwen 3.7 Max55.7#160
4DeepSeek V4 Pro53.3#201
5GLM-5.152.1#200
6Qwen 3.6 Max51.9#192
7DeepSeek V4 Flash51.4#273
8Qwen 3.7 Plus51#221
9Qwen 3.6 Plus50.7#245
10Claude Opus 4.847.6#64
11Claude Opus 4.747.4#86
12Kimi K2.645.2#197
13GPT-5.526.7#56
14Claude Sonnet 518.3#124

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-openclaw-search-strict-success · How It Works · Data refreshed daily, snapshot 2026-11-22.