Google News AI Safety Evaluation

Google News AI Safety Evaluation · August 18, 2026 07:47

Kakao’s Kanana-2 tops Korea safety benchmark, beating Gemma and Qwen - CHOSUNBIZ - Chosunbiz

Kakao’s Kanana-2 tops Korea safety benchmark, beating Gemma and Qwen - CHOSUNBIZ Chosunbiz

Topics: Benchmarks

Entities: Benchmarks

Google News AI Safety Evaluation · August 18, 2026 04:37

Kakao's Lightweight AI Model 'Kanana-2' Outperforms Google and Alibaba in Safety Evaluation - 아시아경제

Kakao's Lightweight AI Model 'Kanana-2' Outperforms Google and Alibaba in Safety Evaluation 아시아경제

Entities: Google

Google News AI Safety Evaluation · August 18, 2026 03:42

Kakao’s Kanana-2 Tops Google, Alibaba Models in Korean AI Safety Benchmark - Koreabizwire

Kakao’s Kanana-2 Tops Google, Alibaba Models in Korean AI Safety Benchmark Koreabizwire

Topics: BenchmarksSafety Evals

Entities: Safety EvalsBenchmarksGoogle

Google News AI Safety Evaluation · August 18, 2026 01:17

Kakao releases safety evaluation results for Kanana-2 AI models, topping global rivals - 헤럴드경제

Kakao releases safety evaluation results for Kanana-2 AI models, topping global rivals 헤럴드경제

Google News AI Safety Evaluation + 1 source (Google News AI Safety Evaluation and Google News Eval Frameworks) · August 12, 2026 05:05

Financial Security Institute Develops Financial AI Safety Evaluation System... Full Operation to Begin Next Year - 아시아경제

Financial Security Institute Develops Financial AI Safety Evaluation System... Full Operation to Begin Next Year 아시아경제

Topics: Safety Evals

Entities: Safety Evals

Google News AI Safety Evaluation + 1 source (Google News AI Safety Evaluation and Google News SWE Bench) · May 09, 2026 08:38

Claude Mythos Shows 50% Time Horizon Of 16+ Hours On METR Benchmark - OfficeChai

Claude Mythos Shows 50% Time Horizon Of 16+ Hours On METR Benchmark OfficeChai

Topics: Benchmarks

Entities: ClaudeBenchmarksMythos