Cybench leaderboard
- Claude Opus 4.6 leads
- 93.0%
- models measured
- 6
- lead over #2
- +11.0 pts
- median
- 51.0%
Leader on Cybench · read October 21
# Cybench, read October 21
leaders = {
"Claude Opus 4.6": 93.0%, "Claude Opus 4.5": 82.0%, "Claude Sonnet 4.5": 60.0%,
}
On October 21, 2026, 6 of our catalog's models had a Cybench result, and Anthropic Claude Opus 4.6 led with 93.0%.
Capture-the-flag security tasks from professional competitions, attempted without hints. Share solved.
Role in the index
A coding board we show beside the Vibe Coding Index, not inside it: the index keeps the four boards it was defined on, so a score does not move every time a board is added. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.6Anthropic | 93.0% | 66.9 | $25.00 | |
| 2 | Claude Opus 4.5Anthropic | 82.0% | 66.8 | $25.00 | |
| 3 | Claude Sonnet 4.5Anthropic | 60.0% | 59.1 | $15.00 | |
| 4 | Claude Opus 4.1Anthropic | 42.0% | 27.2 | $75.00 | |
| 5 | o3 MiniOpenAI | 22.5% | 52.1 | $4.40 | |
| 6 | GPT-4o (2024-11-20)OpenAI | 12.5% | 18.2 | $10.00 |
Only models in our catalog are listed, and each appears once with its best published run. 197 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out.