SUREON - Open-Ended (LLM Judge): leaderboard
Metric: Open-ended answer score (0-1 times 100) from a Claude Opus 4.6 judge of semantic equivalence to the reference, averaged over the 12 categories of the 354-question expert-validated SUREON benchmark; higher is better. Source: arxiv.org. Saturation forecast: Around March 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 | 34 | #131 |
| 2 | Gemini 3.1 Pro (Preview) | 31 | #54 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=sureon-open-ended-llm-judge · How It Works · Data refreshed daily, snapshot 2026-10-11.