Chart puts Kimi K3 at the top of publicly usable cyber models
zainhas · x · 2026-07-25
- The chart ranks overall cyber capability across several Chinese models and shows Kimi K3 at the top of the publicly usable set.
- Other plotted points include GLM 5.2, DeepSeek V4 Pro, Kimi K2.6, Kimi K2.5, Kimi K2 Thinking, DeepSeek V3.1, DeepSeek R1-0528, Alibaba Qwen3, and DeepSeek R1.
- The post notes that the blue-line model is gated and not generally available, implying the strongest-looking line on the chart is not broadly accessible.
Related event: Kimi K3 Cybersecurity Eval Sparks Debate: Scores 32.2%(5 posts)→
More from Models
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11