RevBench (Polyvor Labs)
Agents analyze supplied artifacts in 22 local reverse engineering puzzles. The verifier checks each submitted answer for an exact match.
The August 2026 leaderboard ranks GPT-5.5 first with 11 of 22 tasks solved. Qwen 3.8 Max solved eight using the same Klyrune agent.
- Made by
- Polyvor Labs
- Released
- August 2026
- Kind
- Capture-the-flag challenges
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Risk
- Cyber offence
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Dangerous capabilities
- Strongest model tested
- GPT-5.5 #21 on the capability index
- Last model added
- August 2026
- Scores refreshed
- November 20th, 2026
GPT-5.5 leads with 50% among models released by August 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-5.5 xhigh 50%
- 2
Qwen 3.8 Max 36.4%
- 3
DeepSeek V4 Flash 0731 max 27.3%
Source: Official RevBench (Polyvor Labs) leaderboard
| # | Model | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | GPT-5.5 | 50% | xhigh, Klyrune | Apr 2026 | Aug 2026 | hub.harborframework.com | Official leaderboard |
| 2 | | 36.4% | Klyrune | Aug 2026 | Aug 2026 | hub.harborframework.com | Official leaderboard |
| 3 | | 27.3% | max, Klyrune | Jul 2026 | Aug 2026 | hub.harborframework.com | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official RevBench (Polyvor Labs) leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official RevBench (Polyvor Labs) leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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%
- ExploitBench - Internal Port In use Agents develop working exploits for recently disclosed vulnerabilities to limit contamination. Scored as arbitrary code execution success rate. GPT-6.2 Astra 53.5%
- Atomic Challenges In use Agents solve 22 skill-level offensive security challenges in vulnerability research, network attack simulation and evasion. Scored as challenges solved. GPT-6 Astra 90.9%
- MiMo Cyber Bench In use Agents do in-house cybersecurity tasks that add to public vulnerability reproduction and exploitation benchmarks. The report gives no task count or grading details. MiMo-V2.6 Pro 81.7%
- PatchBench (OpenAI) In use Models patch security flaws. Automated tests and model-based review check that each patch fixes the flaw, keeps the intended behavior and is ready to merge. GPT-6.2 Astra 79.7%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (3 entries).
- Note Models scored Only 3 models we track.
- Pass Newest score The newest is from August 2026, for Qwen 3.8 Max.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
- Pass Headroom The best is 50%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on hub.harborframework.com: 3 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.