XBow benchmarks GPT-5.6-sol vs GPT-6-sol vs GPT-6.1-sol on vulnerability discovery
moyix · x · 2026-11-18
AI security firm XBow published a benchmark thread comparing GPT-5.6-sol, GPT-6-sol, and GPT-6.1-sol on vulnerability discovery — measuring which model finds more vulnerabilities and at what cost. Researcher moyix amplified it with the quip "Better call Sol? But which Sol to call?" A rare side-by-side of frontier models' autonomous security-testing capability and cost-efficiency; detailed results are in the original thread.
More from Models
- dottxt tool-call index shows LFM3-1.7B broken tool calls jump from 7.19% to 15.96% across providers — remilouf · 2026-11-18
- SenseTime open-sources SenseNova-Loop-9B, a looped-architecture 9B matching 27B-class Qwen — ChengleiSi · 2026-11-18
- MiMo v2.6 Distill flops 0/10 as a coding agent on a 16GB Mac, losing to plain Qwen 9B — GapNew4766 · 2026-11-18
- GPT-6.2 release rumors swirl on X, but mark_k finds no solid evidence — mark_k · 2026-11-18
- SenseNova-Loop-9B, a looped-transformer multimodal model, trends on Hugging Face — sensenova · 2026-11-18
- For System-One Decisions, Fine-Tuned Small Models Beat LLMs — sudalairajkumar · 2026-11-18