CyberChainBench - Detect: leaderboard

Metric: Detection reward (%; 1 when both the root-cause vulnerability type and the vulnerable function match the ground truth, else 0; all 541 cases; each model runs in its own agent harness (Claude Code, Codex, Gemini CLI or OpenCode) with the benchmark's on-chain MCP tools in a Harbor container, 30-minute budget, best validated attempt). Source: arxiv.org. Saturation forecast: Around December 2027. 10 models tracked.

Top models

#ModelScore
1GPT-5.5 (Codex)37.5
2Claude Opus 4.7 (Claude Code)33.8
3GPT-5.4 (Codex)32.5
4Claude Opus 4.6 (Claude Code)30.9

Interactive version: theaggregate.ai/benchmark?slug=cyberchainbench-detect · How It Works · Data refreshed daily, snapshot 2026-09-26.