Kimi K3 Cybersecurity Test: Better Cost-Performance Than GPT
shakoistsLog · x · 2026-07-19
In a private cybersecurity benchmark, Kimi K3 demonstrated exceptional cost-performance, acting as the workhorse for security tasks.
- S-Class: GPT 5.6 has the best recall and precision, but costs over 7 times more per run than Kimi K3.
- Best Cost-Performance: Kimi K3 maintains a high recall rate while keeping costs extremely low.
The original author commented that Chinese open-source models are becoming the gold standard in the security domain, while criticizing the work of social scientists at major AI labs and their index systems as extremely poor.
Related event: Kimi K3 Shows High Cost-Performance in Cybersecurity Tests(2 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- 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