AgenticVBench (OpenCode): leaderboard
Metric: Average Normalized Score (%). Source: agenticvbench.com. Saturation forecast: Around August 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 27.4 |
| 2 | Gemini 3.1 Pro (Preview) | 23.8 |
| 3 | MiniMax-M3 | 22.7 |
| 4 | Claude Opus 4.7 | 20.3 |
| 5 | Gemini 3 Flash (Preview) | 17.5 |
| 6 | Claude Sonnet 4.6 | 14.4 |
| 7 | GPT-5.4 Mini | 13.7 |
| 8 | Qwen 3 VL 235B A22B Instruct | 3 |
Interactive version: theaggregate.ai/benchmark?slug=agenticvbench-opencode · How It Works · Data refreshed daily, snapshot 2026-10-09.