activeAgents
SEC-Bench Pro
Metric: Pass@1 (higher is better)Introduced: 2026
Security-focused agent benchmark for professional-grade offensive and defensive security workflows. DeepSeek V4.1 Flash launch materials evaluate with the Claude Code harness.
Models ranked
3
tracked on this benchmark
Score band
66.3 – 47.5
best → lowest tracked
Snapshot trend
-5.90
Sep 10 → Oct 9 · 2 models
Leaderboard
Tracked models ranked by Pass@1 (higher is better).
#Model variant and provenanceRelative to leaderScore
166.3
Version: SEC Bench ProHarness: Not recordedEvaluator: Not recordedObserved: Oct 9, 2026Confidence: Not recordedSource
262.8
Version: SEC-Bench Pro Pass@1; Claude Code harness; max reasoning effortHarness: Not recordedEvaluator: Not recordedObserved: Sep 10, 2026Confidence: Not recordedSource
347.5
Version: SEC Bench ProHarness: Not recordedEvaluator: Not recordedObserved: Oct 9, 2026Confidence: Not recordedSource
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Sep 10, 2026