OfficePrism-420 - OpenClaw (Search) - NL-DB Pass: leaderboard

OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (OpenClaw (Search) - NL-DB Pass) across 420 tasks in 7 business functions.

Metric: Joint NL-DB Pass 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 K372.1#62
2Qwen 3.7 Max69#160
3GLM-5.267.6#154
4DeepSeek V4 Pro65.5#201
5GLM-5.165.5#200
6Qwen 3.6 Max65.2#192
7Qwen 3.6 Plus64.5#245
8Claude Opus 4.763.3#86
9Qwen 3.7 Plus62.9#221
10DeepSeek V4 Flash62.1#273
11Claude Opus 4.861.4#64
12Kimi K2.659.8#197
13GPT-5.532.9#56
14Claude Sonnet 522.6#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-nl-db-pass · How It Works · Data refreshed daily, snapshot 2026-11-22.