OfficePrism-420 - OpenClaw (Full) - Strict Success: leaderboard
OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (OpenClaw (Full) - 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 July 2027. 10 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.2 | 55.5 | #154 |
| 2 | Kimi K3 | 54.3 | #62 |
| 3 | DeepSeek V4 Pro | 52.4 | #201 |
| 4 | GLM-5.1 | 50 | #200 |
| 5 | Qwen 3.7 Max | 49.3 | #160 |
| 6 | DeepSeek V4 Flash | 49 | #273 |
| 7 | Qwen 3.7 Plus | 47.1 | #221 |
| 8 | Qwen 3.6 Plus | 46.7 | #245 |
| 9 | Qwen 3.6 Max | 46 | #192 |
| 10 | Kimi K2.6 | 44.5 | #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-openclaw-full-strict-success · How It Works · Data refreshed daily, snapshot 2026-11-22.