OfficePrism-420 - Claude Code (Search) - NL-DB Pass: leaderboard
OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (Claude Code (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: Around March 2027. 14 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.2 | 74.3 | #154 |
| 2 | Kimi K3 | 72.9 | #62 |
| 3 | Qwen 3.7 Max | 72.6 | #160 |
| 4 | Qwen 3.7 Plus | 72.6 | #221 |
| 5 | Claude Opus 4.8 | 72.4 | #64 |
| 6 | GLM-5.1 | 72.4 | #200 |
| 7 | DeepSeek V4 Pro | 72.1 | #201 |
| 8 | Claude Opus 4.7 | 71.9 | #86 |
| 9 | Qwen 3.6 Max | 71.2 | #192 |
| 10 | DeepSeek V4 Flash | 69.5 | #273 |
| 11 | Qwen 3.6 Plus | 69 | #245 |
| 12 | Claude Sonnet 5 | 68.8 | #124 |
| 13 | GPT-5.5 | 62.4 | #56 |
| 14 | Kimi K2.6 | 62.4 | #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-nl-db-pass · How It Works · Data refreshed daily, snapshot 2026-11-22.