Benchmark Almanac

Capture the Flag (Internal)

GPT-5.6 Sol 97.1% leads since June 2026
Fading

Agents solve 63 public CTF challenges chosen for low GPT-5.3-Codex solve rates, using a Linux box with security tools. Scored as task success rate.

OpenAI says this set is harder than and different from the CTF sets it reported before GPT-5.6.

Made by
OpenAI
Released
June 2026
Kind
Capture-the-flag challenges
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Strongest model tested
GPT-5.6 Sol #13 on the capability index
Last in a launch post
April 2026, dropped after it saturated
Last model added
August 2026
4
Models scored in lab cards
1
Launch post lists it, from 1 lab
8
System cards report it, from 1 lab

GPT-5.6 Sol leads with 97.1% among models released by July 2026

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.

The newest model with a score here came out in July 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 97.1 GPT-5.6 Sol
  2. 93.2 GPT-5.6 Luna
  3. 91.8 GPT-5.6 Terra
  4. 88.1 GPT-5.5
  1. 1 GPT-5.6 Sol 97.1%
  2. 2 GPT-5.6 Luna 93.2%
  3. 3 GPT-5.6 Terra 91.8%
  4. 4 GPT-5.5 88.1%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 GPT-5.6 Sol 97.1% Aug 2026 Lab model card
2 GPT-5.6 Luna 93.2% Aug 2026 Lab model card
3 GPT-5.6 Terra 91.8% Jun 2026 Lab model card
4 GPT-5.5 88.1% Apr 2026 Lab model card

2 models have held number one in labs’ own numbers since its release in June 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Lab claims Passed 85% in Jun 2026, by GPT-5.5
GPT-5.6 Sol 97.1%

Source: Labs’ model cards

OpenAI’s own number for GPT-5.5 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 Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol GPT-5.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol GPT-5.5

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.

OpenAI
DateLaunch postScoreAs the post writes it
Apr 23, 2026 GPT-5.5 88.1 Capture-the-Flags challenge tasks (Internal)

8 system cards report it, from 1 lab

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Aug 6, 2026 GPT-5.6 Sol system card addendum 97.1 Capture the Flag (CTF) Challenges, 63 challenges, pass@12, representative checkpoint, printed chart label (Figure 7, 7.1.2.1.1) Cyber risk
Aug 6, 2026 GPT-5.6 Luna system card addendum 93.2 Capture the Flag (CTF) Challenges, 63 challenges, pass@12, representative checkpoint, printed chart label (Figure 7, 7.1.2.1.1) Cyber risk
Jul 9, 2026 GPT-5.6 Terra system card 91.8 Capture-the-Flags challenge tasks (Internal), 63 challenges, pass@1, printed chart label (Figure 30, 9.1.2.1.1) Cyber risk
Jul 9, 2026 GPT-5.6 Sol system card 96.7 Capture-the-Flags challenge tasks (Internal), 63 challenges, pass@1, printed chart label (Figure 30, 9.1.2.1.1) Cyber risk
Jul 9, 2026 GPT-5.6 Luna system card 85.2 Capture-the-Flags challenge tasks (Internal), 63 challenges, pass@1, printed chart label (Figure 30, 9.1.2.1.1) Cyber risk
Jun 25, 2026 GPT-5.6 Terra system card 91.8 Capture-the-Flags challenge tasks (Internal), 63 challenges, pass@1, printed chart label (Figure 30, 9.1.2.1.1) Cyber risk
Jun 25, 2026 GPT-5.6 Sol system card 96.7 Capture-the-Flags challenge tasks (Internal), 63 challenges, pass@1, printed chart label (Figure 30, 9.1.2.1.1) Cyber risk
Jun 25, 2026 GPT-5.6 Luna system card 85.2 Capture-the-Flags challenge tasks (Internal), 63 challenges, pass@1, printed chart label (Figure 30, 9.1.2.1.1) Cyber risk

More in Cybersecurity

All 115 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%