OfficePrism-420 - Claude Code (Search) - Strict Success: leaderboard

OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (Claude Code (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
1GLM-5.261.2#154
2GLM-5.160#200
3Qwen 3.7 Max59.8#160
4Qwen 3.7 Plus59#221
5Kimi K358.8#62
6DeepSeek V4 Pro57.6#201
7Claude Opus 4.756.9#86
8Qwen 3.6 Max56.9#192
9DeepSeek V4 Flash56#273
10Claude Opus 4.855.7#64
11Qwen 3.6 Plus55.5#245
12Claude Sonnet 554.5#124
13GPT-5.551.9#56
14Kimi K2.650#197

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