GPT-6 Astra xhigh is second at 37.79 and $63.70. On this recorded benchmark configuration, Sol achieved the higher score at roughly 80% lower listed run cost. The comparison is a benchmark-specific operating signal, not a general security or model-quality ranking.
Raw SignalSep 25, 20261 min read1 source
GPT-6 Sol now leads DeepSecBench's Pareto frontier: • Highest benchmark score • 80% lower run cost than the runner-up (GPT-6 Astra) https://t.co/ZmDC4NmjSQ https://t.co/soK5ZM0RdD
In one minute
Vercel AI Gateway's DeepSecBench leaderboard lists GPT-6 Sol xhigh first with a 40.91 score, 35.8% recall, 96.0% precision, four false positives, and a $12.76 run cost using the Codex harness.