Benchmark Almanac

CTF-Archive Diamond

GPT-5.5 71% leads since May 2026
Not in model cards

Agents solve 285 difficult capture-the-flag tasks drawn from the pwn.college cybersecurity platform. Scores measure the share of tasks solved.

NIST reports six current models on this CAISI-developed selection, including GPT-5.5 at 71%, Opus 4.6 at 46%, and DeepSeek V4 Pro at 32%.

Made by
US CAISI (NIST)
Released
May 2026
Kind
Capture-the-flag challenges
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Items from
Another benchmark
Refresh
One fixed set
Run by
A host
Based on
CTF-Archive
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
June 2026
Scores refreshed
November 21st, 2026
6
Models scored on its own leaderboard

GPT-5.5 leads with 71% among models released by June 2026

Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best.

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

  1. 1 GPT-5.5 x-high 71%
  2. 2 Claude Mythos Preview 65.6%
  3. 3 Claude Opus 4.8 not reported 48.4%
  4. 4 Claude Opus 4.6 max 46%
  5. 5 GLM-5.2 max 39.3%
  6. 6 GPT-5.4 Mini x-high 32%

Source: Official CTF-Archive Diamond leaderboard

#ModelScoreSettingDateSource
1 GPT-5.5 71% x-high, CAISI Inspect ReAct agent Apr 2026 Official leaderboard
2 Claude Mythos Preview 65.6% CAISI Inspect ReAct agent Apr 2026 Official leaderboard
3 Claude Opus 4.8 48.4% not reported, CAISI Inspect ReAct agent May 2026 Official leaderboard
4 Claude Opus 4.6 46% max, CAISI Inspect ReAct agent Feb 2026 Official leaderboard
5 GLM-5.2 39.3% max, CAISI Inspect ReAct agent Jun 2026 Official leaderboard
6 GPT-5.4 Mini 32% x-high, CAISI Inspect ReAct agent Mar 2026 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard Not tested since Jun 2026
GPT-5.5 71%

Source: Official CTF-Archive Diamond leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5 Claude Mythos Preview Claude Opus 4.6 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5 Claude Opus 4.6

Source: Official CTF-Archive Diamond 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

All 138 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 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from June 2026, for GLM-5.2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Pass Headroom The best is 71%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on atlas.village.dev: 6 rows for models we track at the last read.
  • Pass Last read November 21st, 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.

How we check