CFAgentBench: leaderboard
CFAgentBench (arXiv) — autonomous agents carrying out end-to-end construction-finance workflows; pass^1 task-success rate (%).
Metric: pass^1 (%). Source: arxiv.org. Saturation forecast: Around January 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V3.1 | 67 | #264 |
| 2 | Qwen 2.5 72B | 54 | #499 |
| 3 | Qwen 3 235B A22B | 45 | #313 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=cfagentbench · How It Works · Data refreshed daily, snapshot 2026-10-20.