FAR.AI Leaderboard: OpenAI and Anthropic Models Outperform Gemini and Grok in Jailbreak Robustness
S_OhEigeartaigh · x · 2026-07-30
AI safety research organization FAR.AI has published a new leaderboard and study evaluating the relative difficulty of jailbreaking frontier language models, revealing significant disparities in robustness.
- Safety Leaders: Models from OpenAI and Anthropic demonstrated notably stronger defenses and overall robustness against attacks.
- Vulnerability: Google's Gemini and xAI's Grok were found to be comparatively easier to jailbreak.
- Recommendations: The organization hopes the benchmark will encourage higher industry-wide safety standards and advocates for the adoption of defense-in-depth strategies to secure AI systems.
Related event: FAR AI Launches LLM Security Leaderboard: Many Models Easily Jailbroken(4 posts)→
More from Models
- Reflection's Beam, a 501B-parameter open MoE model with 1M context, lands on Hugging Face under Apache 2.0 — QGallouedec · 2026-10-16
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16