Skip to main content

Benchmark profile

ACE Cyber Range Challenges Solved (ACE solved)

Number of advanced cyber-range challenges solved in the joint NIST CAISI and UK AISI preliminary evaluation.

Data verified

Benchmark score on ACE solved — July 24, 2026

BenchLM mirrors the published score view for ACE solved. Kimi K3 leads the public snapshot at 0%. BenchLM does not use these results to rank models overall.

1 modelExternal benchmark mirrorsCurrentDisplay onlyUpdated July 24, 2026

Benchmark score table (1 model)

Score
1
Kimi K3Moonshot AI · Closed
0%

About ACE solved

Year

2026

Tasks

41 advanced cyber-range challenges

Format

Challenges solved

Difficulty

Advanced cyber operations

The preliminary assessment tested 41 ACE challenges. This is a display-only security result from a controlled government evaluation.

BenchLM freshness & provenance

Version

ACE solved 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does ACE solved measure?

Number of advanced cyber-range challenges solved in the joint NIST CAISI and UK AISI preliminary evaluation.

Which model scores highest on ACE solved?

Kimi K3 by Moonshot AI currently leads with a score of 0% on ACE solved.

How many models are evaluated on ACE solved?

1 AI models have been evaluated on ACE solved on BenchLM.

Last updated: July 24, 2026 · BenchLM version ACE solved 2026