VibeSearchBench: leaderboard

Metric: Triplet F1 (%; an LLM judge matches the knowledge graph the agent extracts after a multi-turn session with a progressive-disclosure user simulator against the annotated ground-truth graph; OpenClaw agent harness; mean of VibeSearch-Pro and VibeSearch-Daily; mean of 3 runs per task). Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.

Top models

#ModelScore
1Claude Opus 4.630.3
2DeepSeek V4 Pro27.64
3Kimi K2.626.17
4Seed 2.0 Pro25.23
5Gemini 3.1 Pro (Preview)23.62
6Qwen 3.5 397B A17B23.1
7GPT-5.421.92

Interactive version: theaggregate.ai/benchmark?slug=vibesearchbench · How It Works · Data refreshed daily, snapshot 2026-09-26.