HAE-GEO - Clean Answer Quality: leaderboard
Deep-search agents on clean web evidence, before any poisoning: semantic rubric score 0-2. Higher is better. Source: arxiv.org/abs/2609.06027.
Metric: Rubric Score (0-2). Source: arxiv.org. Saturation forecast: Around July 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 397B A17B | 1.53 | #154 |
| 2 | GPT-5.6 Sol | 1.53 | #22 |
| 3 | Qwen 3.6 35B A3B | 1.53 | #239 |
| 4 | MiniMax-M3 | 1.45 | #151 |
| 5 | Kimi K3 | 1.43 | #35 |
| 6 | Qwen 3.8 27B | 1.43 | #125 |
| 7 | GLM-5.2 | 1.42 | #79 |
| 8 | Claude Opus 4.8 | 1.35 | #40 |
| 9 | DeepSeek V4 Flash | 1.34 | #155 |
| 10 | GLM-4.7 Flash | 1.18 | #543 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=hae-geo-clean-answer-quality · How It Works · Data refreshed daily, snapshot 2026-11-06.