Benchmark Almanac

CTI-to-MITRE

SecureBERT 72.5% tops its leaderboard
Not in model cards

Models classify a threat description using MITRE ATT&CK technique labels. The HELM scenario presents a set of candidate labels.

Released
August 2022
Kind
Secure code and review
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
11
Entries in its paper, 0 models we track

SecureBERT tops the leaderboard with 72.5%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 SecureBERT 72.5%
  2. 2 MLP 70.4%
  3. 3 SVM (OvO) 69.9%
  4. 4 SVM (OvR) 69.9%
  5. 5 Logistic Regression (balanced) 64.6%
  6. 6 Complement Naive Bayes 63.9%
  7. 7 CNN 61.4%
  8. 8 LSTM (Word2vec) 61%
  9. 9 LSTM 57.7%
  10. 10 Logistic Regression 55.6%
  11. 11 Multinomial Naive Bayes 36.8%

Source: The CTI-to-MITRE paper

#EntryScoreSettingDateSource
1 SecureBERT 72.5% Official leaderboard
2 MLP 70.4% Official leaderboard
3 SVM (OvO) 69.9% Official leaderboard
4 SVM (OvR) 69.9% Official leaderboard
5 Logistic Regression (balanced) 64.6% Official leaderboard
6 Complement Naive Bayes 63.9% Official leaderboard
7 CNN 61.4% Official leaderboard
8 LSTM (Word2vec) 61% Official leaderboard
9 LSTM 57.7% Official leaderboard
10 Logistic Regression 55.6% Official leaderboard
11 Multinomial Naive Bayes 36.8% Official 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 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (11 entries).
  • Pass Models scored 11 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 11 entries at the last read, none a model we track.
  • 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.

How we check