AgentEvalBench (LLM-Singleturn): leaderboard
Metric: Eval@1 (%; share of 40 cases, 20 agents under generic and specific requirements, whose generated evaluation code runs and yields non-vacuous results on real agent traces at the first attempt; single prompt with the agent code, traces and requirements, no tools). Source: arxiv.org. Saturation forecast: Around July 2028. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 17.5 |
| 2 | Claude Haiku 4.5 | 15 |
Interactive version: theaggregate.ai/benchmark?slug=agentevalbench-llm-singleturn · How It Works · Data refreshed daily, snapshot 2026-09-26.