HoF-Bench (No Context): leaderboard
Metric: CVEs rediscovered at pass@4 (out of 95), without the generated-context stage, on 95 public AI-discovered CVEs in eight repositories pinned at vulnerable commits, found by a minimal fixed LLM scanner scaffold with four repeated passes and multi-round triage, credited only when a detector-blinded GPT-5.6 terra judge matches code path, root cause, attack condition and impact; medium reasoning effort where supported. Source: arxiv.org. Saturation forecast: Around August 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Luna (Medium) | 65 |
| 2 | GPT-5.4 Mini (Medium) | 57 |
| 3 | DeepSeek V4 Flash | 56 |
| 4 | Gemini 3.5 Flash (Medium) | 53 |
| 5 | Qwen 3.6 35B A3B | 49 |
| 6 | GPT-OSS-120B | 48 |
| 7 | GPT-5.4 Nano (Medium) | 47 |
| 8 | Gemini 2.5 Flash (Medium) | 42 |
| 9 | GPT-OSS-20B | 40 |
| 10 | Mistral Small 4 | 36 |
Interactive version: theaggregate.ai/benchmark?slug=hof-bench-no-context · How It Works · Data refreshed daily, snapshot 2026-09-29.