DailySafe - Helpfulness Rate (HR): leaderboard
DailySafe (arXiv 2611.26298v1) dynamic multimodal safety benchmark (Helpfulness Rate (HR)) over 195 everyday multi-turn image-text cases.
Metric: Helpfulness Rate (%, 3-run mean over 195 multi-turn multimodal cases). Source: arxiv.org. Saturation forecast: Around February 2027. 16 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 94.53 | #9 |
| 2 | GPT-6 Sol | 94.53 | #33 |
| 3 | Gemini 3.8 Flash | 87.52 | #43 |
| 4 | GPT-5.6 Sol | 85.3 | #36 |
| 5 | Gemini 3.1 Pro (Preview) | 84.96 | #102 |
| 6 | Kimi K3 | 77.78 | #62 |
| 7 | Gemini 3.5 Flash | 76.07 | #110 |
| 8 | GLM-5.3 Flash | 69.57 | #137 |
| 9 | Qwen3.8-Flash-Next | 62.22 | #122 |
| 10 | Claude Sonnet 5 | 60.51 | #124 |
| 11 | MiMo-V2.6-Pro | 52.31 | #94 |
| 12 | Qwen 3.8 27B | 47.86 | #232 |
| 13 | DeepSeek V4.1 Flash | 44.44 | #69 |
| 14 | MiMo-V2.6-Flash | 36.07 | #183 |
| 15 | Qwen 3 VL 8B (Thinking) | 8.38 | #924 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=dailysafe-helpfulness-rate-hr · How It Works · Data refreshed daily, snapshot 2026-11-22.