OfficePrism-420 - DeepAgents (Full) - Strict Success: leaderboard
OfficePrism-420 (arXiv 2611.22262) single-domain enterprise agent evaluation (DeepAgents (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 August 2027. 14 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 | 58.8 | #62 |
| 2 | Claude Opus 4.8 | 58.1 | #64 |
| 3 | Claude Sonnet 5 | 58.1 | #124 |
| 4 | GPT-5.5 | 56.4 | #56 |
| 5 | Claude Opus 4.7 | 56.4 | #86 |
| 6 | GLM-5.2 | 56 | #154 |
| 7 | DeepSeek V4 Pro | 53.6 | #201 |
| 8 | DeepSeek V4 Flash | 53.6 | #273 |
| 9 | GLM-5.1 | 53.6 | #200 |
| 10 | Qwen 3.7 Max | 51.7 | #160 |
| 11 | Kimi K2.6 | 51.4 | #197 |
| 12 | Qwen 3.7 Plus | 51.4 | #221 |
| 13 | Qwen 3.6 Plus | 51.2 | #245 |
| 14 | Qwen 3.6 Max | 49.8 | #192 |
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-deepagents-full-strict-success · How It Works · Data refreshed daily, snapshot 2026-11-22.