KGC-Safety (LG)
K-EXAONE 2.0 99.8% leads since Jul 2026 Fading Models answer risky prompts set in Korean social and cultural contexts. A Safe Rate is scored over four domains: universal human values, social safety, Korean sensitivity and future risk.
LG introduced it in the K-EXAONE technical report. It is built on LG's K-AUT risk taxonomy, which grew from 226 to 296 risk areas in its second version.
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
K-EXAONE 2.0 leads with 99.8%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 K-EXAONE 2.0 99.8%
- 2 K-EXAONE 96.1%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | K-EXAONE 2.0 | 99.8% | Jul 2026 | Model card | |
| 2 | K-EXAONE | 96.1% | Dec 2025 | Model card |
2 models have held number one since its release in Jan 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
The best score passed 85% in Dec 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs headline it less often now, last in Jul 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 31 Jul 2026 | K-EXAONE 2.0 | 99.8 | KGC-Safety (in-house, Safe Rate) |
| 31 Dec 2025 | K-EXAONE | 96.1 | KGC-Safety |
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 5 Aug 2026 | K-EXAONE 2.0 technical report | 99.8 | KGC-Safety (in-house), Total Safe Rate (Tables 6 and 11) | Safety |
| 5 Jan 2026 | K-EXAONE technical report | 96.1 | KGC-Safety (in-house) Total Safe Rate (Tables 3 and 9). Universal Human Values 97.5, Social Safety 96.9, Korean Sensitivity 94.3, Future Risk 95. Non-reasoning 88.4 | Safety |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy.
Muse Spark Open 98.1% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%