DailySafe (Single-Turn Consolidated) - Safety Rate (SR): leaderboard

DailySafe (arXiv 2611.26298v1) dynamic multimodal safety benchmark (Safety Rate (SR)) over 195 everyday multi-turn image-text cases.

Metric: Single-turn consolidated Safety Rate (%, 3-run mean). Source: arxiv.org. Saturation forecast: Around February 2027. 16 models tracked. Updated 22 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 5.592.82#9
2GPT-6 Sol89.74#33
3Gemini 3.8 Flash88.21#43
4GPT-5.6 Sol87.35#36
5Gemini 3.1 Pro (Preview)82.39#102
6Gemini 3.5 Flash77.26#110
7Kimi K370.94#62
8GLM-5.3 Flash63.93#137
9Claude Sonnet 556.07#124
10Qwen3.8-Flash-Next54.87#122
11Qwen 3.8 27B39.49#232
12MiMo-V2.6-Pro36.07#94
13DeepSeek V4.1 Flash31.62#69
14MiMo-V2.6-Flash19.83#183
15Qwen 3 VL 8B (Thinking)5.13#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-single-turn-consolidated-safety-rate-sr · How It Works · Data refreshed daily, snapshot 2026-11-22.