AJ-Bench (LLM-as-a-Judge) - Deep Search: leaderboard
Verifying agent trajectories on AJ-Bench (2026), the Deep Search subdomain (156 trajectories of multi-hop web research tasks): the judge decides whether each trajectory succeeded and is scored against binary human-verified labels. In this setting the judge reads the trajectory only, with no tools or environment access. F1 in percent; higher is better.
Metric: F1 (%) on Deep search (Mind2Web 2-derived items; 52 tasks, 156 trajectories), averaged over three runs, with the judge reading the trajectory only (no tools or environment access), of AJ-Bench, judging whether agent trajectories succeeded against binary human-verified labels (155 tasks, 516 trajectories), default model configurations; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | LongCat-Flash-Chat | 81.8 | #820 | |
| 2 | Claude Sonnet 4.5 | 81.34 | #267 | |
| 3 | Qwen 3 235B A22B | 81.33 | #633 | |
| 4 | Gemini 3 Pro (Preview) | 81.26 | #123 | |
| 5 | Gemini 2.5 Pro | 81.22 | #280 | |
| 6 | Claude Opus 4.5 | 81.11 | #165 | |
| 7 | GPT-5 | 80.37 | #185 | |
| 8 | Kimi K2 0905 | 80.17 | #578 | |
| 9 | Grok 4 | 78.32 | #321 | |
| 10 | GLM-4.6 | 77.88 | #496 | |
| 11 | GPT-5.1 | 70.9 | #248 | |
| 12 | GPT-5 Mini | Low | 68.42 | #373 |
| 13 | DeepSeek V3.2 | 62.91 | #425 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=aj-bench-llm-as-a-judge-deep-search · How It Works · Data refreshed daily, snapshot 2026-11-22.