cd /news/ai-safety/uk-s-ai-security-institute-finds-sta… · home › topics › ai-safety › article
[ARTICLE · art-47709] src=the-decoder.com ↗ pub= topic=ai-safety verified=true sentiment=· neutral

UK's AI Security Institute finds standard benchmarks systematically underestimate what AI agents can actually do

The UK's AI Security Institute (AISI) found that standard AI benchmarks systematically underestimate agent capabilities by limiting compute budgets. In a study of seven benchmarks, increasing the token budget tenfold boosted success rates on software engineering tasks by about 25 percent, with newer models benefiting most. AISI estimates actual progress at the frontier is roughly 60 percent steeper than previously measured.

read1 min views1 publishedJul 3, 2026

In a study covering seven benchmarks, the UK's AI Security Institute shows that standard AI evaluations systematically underestimate agent capabilities by capping the compute budget. On software engineering tasks, success rates jumped about 25 percent when the token budget was increased tenfold. Newer models benefit the most. Depending on the token budget, actual progress at the frontier is about 60 percent steeper than previous measurements suggested, according to AISI.

The article UK's AI Security Institute finds standard benchmarks systematically underestimate what AI agents can actually do appeared first on The Decoder.

source & further reading
the-decoder.com — original article Mistral's open-source Leanstral 1.5 aces formal math benchmarks and catches real bugs in code Microsoft follows Anthropic and OpenAI into the AI super app race with overhauled Copilot and AutoPilot agents Claude Code's complicated China problem involves bans on both sides of the Pacific
── more in #ai-safety 4 stories · sorted by recency
── more on @uk's ai security institute 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/uk-s-ai-security-ins…] indexed:0 read:1min 2026-07-03 · —