SGR-Bench: leaderboard
Recent advances in large language models and tool-using agents have expanded the range of benchmarked web tasks. Yet an important class of specialized retrieval tasks remains undercharacterized. On many specialized data-retrieval websites, answer-bearing evidence becomes accessible only after establishing the correct site-specific retrieval state through filters, views, hierarchies, or scopes. We
Metric: Item-F1 (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 66.18 | #31 |
| 2 | GLM-5.1 | 65.64 | #97 |
| 3 | Claude Opus 4.7 | 61.38 | #49 |
| 4 | DeepSeek V4 Pro | 60.98 | #102 |
| 5 | Gemini 3.1 Pro (Preview) | 59.06 | #58 |
| 6 | Kimi K2.5 | 47.39 | #144 |
| 7 | Qwen 3.6 Plus | 36.88 | #120 |
| 8 | Seed 2.0 Pro | 29.88 | #118 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sgr-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.