V8 JavaScript EngineBrowse 284 families
V8 JavaScript Engine
Can the model diagnose or complete difficult cybersecurity tasks?
Version / measure
- Domain
- Cybersecurity
- Ranked models
- 3
- Reported values
- 3
- Reports
- 1 · lab
- Direction
- Higher is better
- Status
- Version not specified
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | Gemini 3.5 Flash CyberGoogle | reportedcost n/a1 value · Jul 21 · source | 55 |
| 2 | Gemini 3.5 FlashGoogle | reportedcost n/a1 value · Jul 21 · source | 47 |
| 3 | Claude Opus 4.6Anthropic | reportedcost n/a1 value · Jul 21 · source | 36 |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarylimited methodology
Can the model diagnose or complete difficult cybersecurity tasks?
Security analysis or exploitation under a controlled evaluation environment. Higher is better. Count of unique confirmed vulnerabilities found across the source's fixed number of invocations.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
The source prints 55 for Gemini 3.5 Flash Cyber, 47 for mainline Gemini 3.5 Flash, and 36 for Claude Opus 4.6; chart-only CyberGym, Big Sleep, and Chrome-pipeline scores are omitted.
Method / source ↗