AJ-Bench (LLM-as-a-Judge) - Excel: leaderboard
Verifying agent trajectories on AJ-Bench (2026), the Excel subdomain (38 trajectories of OSWorld spreadsheet 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 Excel GUI tasks (OSWorld; 19 tasks, 38 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: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.5 | 75.77 | #160 | |
| 2 | Grok 4 | 75.52 | #319 | |
| 3 | Gemini 3 Pro (Preview) | 74.28 | #119 | |
| 4 | GLM-4.6 | 72.49 | #498 | |
| 5 | Claude Sonnet 4.5 | 71.24 | #261 | |
| 6 | DeepSeek V3.2 | 70.12 | #419 | |
| 7 | Gemini 2.5 Pro | 66.67 | #276 | |
| 8 | GPT-5 Mini | Low | 64.36 | #364 |
| 9 | Kimi K2 0905 | 63.9 | #570 | |
| 10 | GPT-5 | 61.78 | #178 | |
| 11 | GPT-5.1 | 60.33 | #240 | |
| 12 | LongCat-Flash-Chat | 55.88 | #818 | |
| 13 | Qwen 3 235B A22B | 53.97 | #628 |
No result here: #1 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-excel · How It Works · Data refreshed daily, snapshot 2026-11-21.