AgenticVBench (OpenClaw): leaderboard
Metric: Average Normalized Score (%). Source: agenticvbench.com. Saturation forecast: Around July 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 21.9 |
| 2 | Claude Opus 4.7 | 21.1 |
| 3 | Claude Sonnet 4.6 | 13.7 |
| 4 | GPT-5.4 Mini | 7.7 |
| 5 | Gemini 3 Flash (Preview) | 5.5 |
| 6 | Qwen 3 VL 235B A22B Instruct | 3.3 |
| 7 | Gemini 3.1 Pro (Preview) | 0.4 |
Interactive version: theaggregate.ai/benchmark?slug=agenticvbench-openclaw · How It Works · Data refreshed daily, snapshot 2026-10-09.