SEC-bench Pro - V8: leaderboard
Metric: V8 instances solved, headline mode (% of 103 instances; timeouts count as unsolved). Source: sec-bench.github.io. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (xHigh) | 47.57 |
| 2 | GPT-5.4 (xHigh) | 34.95 |
| 3 | Kimi K2.5 (High) | 1.94 |
Interactive version: theaggregate.ai/benchmark?slug=sec-bench-pro-v8 · How It Works · Data refreshed daily, snapshot 2026-09-19.