PerceptRL Agentic - TreeBench: leaderboard
PerceptRL tests visual understanding and spatial reasoning, with separate results for single-turn answers and agents using tools. Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around September 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4.5 | 64 | #53 |
| 2 | Gemini 3 Flash | 62.2 | #103 |
| 3 | Claude Opus 4.8 | 59 | #39 |
| 4 | Qwen 3.6 35B A3B | 56.5 | #233 |
| 5 | Qwen 3.5 Flash | 56.3 | #235 |
| 6 | Kimi K2.6 | 54.8 | #111 |
| 7 | Doubao Seed 2.0 Mini | 54.6 | #160 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=perceptrl-agentic-treebench · How It Works · Data refreshed daily, snapshot 2026-10-29.