Kimi K3 trails leading U.S. frontier models in preliminary cyber tests
HZoete · x · 2026-07-24
A user comments on a quick test of Kimi K3 after citing AISecurityInst’s preliminary cyber evaluation with NIST.
The cited evaluation says Kimi K3 scores below leading US frontier models on the initial cyber-capability benchmarks, so this is mainly a model-ability comparison rather than a product announcement.
More from Models
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- Meta's Muse Agent has built-in invite code logic, hinting at free-usage expansion — testingcatalog · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Claude is no longer available for minors as Anthropic rolls out age assurance — Muhammad523 · 2026-09-11