XBOW Validation Benchmarks
Claude Opus 4.7 98.5%
Fading Offensive security agents attack deliberately vulnerable web applications and must capture a flag to prove each exploit.
About 750 GitHub stars, and pentest agent makers still quote scores on it. XBOW itself says the set was saturated by mid-2026 and the bugs are in training data.
- Made by
- XBOW
- Released
- August 2024
- Kind
- Capture-the-flag challenges
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- Claude Opus 4.7 #30 on the capability index
- Last in a launch post
- April 2026, dropped after it saturated
- Last model added
- April 2026
1
Model scored in lab cards
1
Launch post lists it, from 1 lab
Claude Opus 4.7 leads with 98.5%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Claude Opus 4.7 98.5%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.7 | 98.5% | Apr 2026 | Lab model card |
Anthropic’s own number for Claude Opus 4.7 passed 85% in April 2026
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
Source: Labs’ model cards
Labs headline it less often now, last in April 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Apr 16, 2026 | Claude Opus 4.7 | 98.5 | XBOW visual-acuity benchmark, 98.5% |
More in Cybersecurity
- ExploitGym In use 869 real-vulnerability exploit-development tasks (userspace, V8, Linux kernel). Success means capturing a flag through the intended vulnerability. GPT-6 Astra 42.4%
- ExploitBench In use 41 recent V8 JavaScript-engine N-day vulnerabilities. Progress measured by 16 grader-verified capability flags across five tiers. GPT-6 Astra 100%
- CyberBench v1.1 (Vals) In use Agents work on OSS-Fuzz memory-safety bugs from ARVO images in two tracks. They write a proof-of-concept input that crashes the target, or patch the source so the crash stops and tests still pass.
Muse Wonder 80.4% - SRE-Bench In use Software reverse engineering without source: 262 binary instances from 19 private programs, each with six graded objectives. GPT-6 Astra 56.9%
- CyScenarioBench In use Scenario-based long-horizon security challenges in sandboxes, organized in task, scenario and campaign tiers. Evaluation set kept private.
Gemini 4 Argon 100% - ExploitBench - Internal Port In use Agents develop working exploits for recently disclosed vulnerabilities to limit contamination. Scored as arbitrary code execution success rate. GPT-6 Cyber 42%