Noometry

Agentic & Tool Use benchmark

Cybench leaderboard

As of October 2026, Claude Opus 4.6 has the highest published Cybench score on Noometry at 93%, out of 21 models with results.

Last verified

About Cybench

Professional capture-the-flag cybersecurity tasks, solved without hints.

Category
Agentic & Tool Use
Introduced
2024
Size
40 tasks
Format
CTF
Unit
Percent (random guessing ≈ 0%)
Official site
cybench.github.io

Top 15 models

  1. Claude Opus 4.6 93%
  2. Claude Opus 4.5 82%
  3. Claude Sonnet 4.5 60%
  4. Grok 4 43%
  5. Claude Opus 4.1 42%
  6. Grok 4.1 39%
  7. Claude Opus 4 38%
  8. Claude Sonnet 4 35%
  9. Grok 4 Fast 30%
  10. o3-mini 22.5%
  11. Claude 3.7 Sonnet 20%
  12. Claude 3.5 Sonnet 17.5%
  13. GPT-4.5 17.5%
  14. GPT-4o 12.5%
  15. Claude 3 Opus 10%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1Claude Opus 4.6 Anthropic93%Epoch AI
2Claude Opus 4.5 Anthropic82%Epoch AI
3Claude Sonnet 4.5 Anthropic60%Epoch AI
4Grok 4 xAI43%Epoch AI
5Claude Opus 4.1 Anthropic42%Epoch AI
6Grok 4.1 xAI39%Epoch AI
7Claude Opus 4 Anthropic38%Epoch AI
8Claude Sonnet 4 Anthropic35%Epoch AI
9Grok 4 Fast xAI30%Epoch AI
10o3-mini OpenAI22.5%mediumEpoch AI
11Claude 3.7 Sonnet Anthropic20%Epoch AI
12Claude 3.5 Sonnet Anthropic17.5%Epoch AI
13GPT-4.5 OpenAI17.5%Epoch AI
14GPT-4o OpenAI12.5%Epoch AI
15Claude 3 Opus Anthropic10%Epoch AI
16o1 OpenAI10%Epoch AI
17o1-mini OpenAI10%mediumEpoch AI
18Gemini 1.5 Pro (May 2024) Google7.5%Epoch AI
19Llama 3.1-405B Meta7.5%Epoch AI
20Mixtral 8x22B Mistral AI7.5%Epoch AI
21Llama 3-70B Meta5%Epoch AI

Compare the leaders

Other agentic & tool use benchmarks

Frequently asked questions

What does Cybench measure?

Professional capture-the-flag cybersecurity tasks, solved without hints.

Which model has the highest Cybench score?

As of October 2026, Claude Opus 4.6 has the highest published Cybench score on Noometry at 93%, out of 21 models with results.

What is the best open-weight model on Cybench?

Llama 3.1-405B has the highest Cybench accuracy among open-weight models at 7.5%, ranking 19 of 21 overall.