DailySafe - Safety Rate (SR): leaderboard

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

Metric: Safety 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

#ModelScoreOverall rank
1Claude Opus 5.592.65#9
2GPT-6 Sol92.48#33
3Gemini 3.1 Pro (Preview)83.42#102
4Gemini 3.8 Flash82.91#43
5GPT-5.6 Sol81.71#36
6Kimi K371.97#62
7Gemini 3.5 Flash70.77#110
8GLM-5.3 Flash63.25#137
9Qwen3.8-Flash-Next55.56#122
10Claude Sonnet 555.04#124
11MiMo-V2.6-Pro45.81#94
12Qwen 3.8 27B42.39#232
13DeepSeek V4.1 Flash41.03#69
14MiMo-V2.6-Flash30.6#183
15Qwen 3 VL 8B (Thinking)6.15#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-safety-rate-sr · How It Works · Data refreshed daily, snapshot 2026-11-22.