PulseAugur
EN
LIVE 19:43:35

Kimi K3 lags US models in cyber exploit tests, distillation suspected · 2 sources tracked

By PulseAugur Editorial · [2 sources] ·

Moonshot AI's Kimi K3 model demonstrated significantly weaker performance on cyber exploit tasks compared to leading US models, scoring 32% on ExploitBench versus 76%. The model's safeguards also proved insufficient in blocking simulated attacks. Researchers suggest that the discrepancy between Kimi K3's strong general benchmark scores and its poor performance on security-focused evaluations may be due to distillation techniques, potentially involving Anthropic's models. AI

IMPACT Highlights potential security vulnerabilities in AI models and suggests that distillation techniques may impact specialized performance.

RANK_REASON The cluster reports on benchmark results for an AI model's performance on specific tasks, which falls under research.

Read on The Decoder →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Kimi K3 lags US models in cyber exploit tests, distillation suspected · 2 sources tracked

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster reports on benchmark results for an AI model's performance on specific tasks, which falls under research.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
safety, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
64 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. The Decoder TIER_1 English(EN) · Matthias Bastian ·

    Kimi K3 trails frontier US models by a wide margin on cyber exploits, and distillation may explain why

    <p><img alt="" class="attachment-full size-full wp-post-image" height="1152" src="https://the-decoder.com/wp-content/uploads/2026/07/aisi_logo_pattern.png" style="height: auto; margin-bottom: 10px;" width="2048" /></p> <p> The British AI Security Institute and the U.S. Center for…

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Kimi K3 scored 32% on ExploitBench vs 76% for top US models, with weak safeguards against cyber exploits. Distillation may explain the gap between its general b

    Kimi K3 scored 32% on ExploitBench vs 76% for top US models, with weak safeguards against cyber exploits. Distillation may explain the gap between its general benchmarks and security performance. # AI # Automation Source: The Decoder AI https:// the-decoder.com/kimi-k3-trails -fr…

    LINKS the-decoder.com/kimi-k3-trails-frontier-u…

RELATED ENTITIES

RELATED TOPICS