Agentick — leaderboard
Universal benchmark for evaluating sequential decision agents across RL, LLM, VLM, modality, harness, task, and category settings.
Metric: Oracle-Normalized Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 30.9 |
| 2 | Gemini 2.5 Flash Lite | 18.7 |
| 3 | Qwen 3.5 2B | 13.3 |
| 4 | Qwen 3.5 0.8B | 9.4 |
| 5 | Qwen 3 4B | 8.5 |
Interactive version: theaggregate.ai/benchmark?slug=agentick · How the rankings work · Data refreshed daily, snapshot 2026-07-22.