SGR-Bench - Goal-Oriented: leaderboard
Item-level F1 in percent for search agents on 100 state-gated retrieval tasks, where answer-bearing records on specialized data sites appear only after the right filters and selections are set (SGR-Bench, 2026), in the formulation that states only the goal and leaves the constraints implicit. Higher is better.
Metric: Item-level F1 (%) on the goal-oriented formulation of the same problems (only the goal is stated, constraints are implicit), 100 state-gated retrieval tasks on specialized data sites (scholarly, official statistics, life science, environmental, regulatory); eight models in production CLI agents (GPT-5.5 in Codex CLI, the others in Claude Code) with the same Serper search, fetch and PDF tools, plus three commercial search agents; outputs parsed into rows and aligned by key fields; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GLM-5.1 | 68.1 | #198 | |
| 2 | DeepSeek V4 Pro | 65.29 | #196 | |
| 3 | GPT-5.5 | 64.15 | #54 | |
| 4 | Gemini 3.1 Pro (Preview) | Medium | 61.7 | #99 |
| 5 | Claude Opus 4.7 | Medium | 58.41 | #85 |
| 6 | Deep Research | 51.14 | ||
| 7 | Kimi K2.5 | Thinking | 45.17 | #266 |
| 8 | Gemini Deep Research | 30.15 | ||
| 9 | Qwen 3.6 Plus | 29.5 | #238 | |
| 10 | Seed 2.0 Pro | Medium | 28.27 | #222 |
| 11 | Google Search AI Mode | 13.01 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=sgr-bench-goal-oriented · How It Works · Data refreshed daily, snapshot 2026-11-21.