Benchmark Almanac

Real-world vulnerability discovery

Gemini 4 Argon 86%
In use

Agents search popular open-source codebases to rediscover about 1,200 recent confirmed vulnerabilities across many languages. Reports share discovered.

In-house Google DeepMind evaluation. The tasks are not public.

Made by
Google DeepMind
Kind
Finding and exploiting real bugs
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Strongest model tested
Gemini 4 Argon #9 on the capability index
Last in a launch post
September 2026
Last model added
October 2026
2
Models scored in lab cards
1
Launch post lists it, from 1 lab
1
System card reports it, from 1 lab

Gemini 4 Argon leads with 86%

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.

  1. 86.0 Gemini 4 Argon
  2. 71.0 Gemini 3.8 Flash Cyber
  1. 1 Gemini 4 Argon 86%
  2. 2 Gemini 3.8 Flash Cyber 71%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Gemini 4 Argon 86% Oct 2026 Lab model card
2 Gemini 3.8 Flash Cyber 71% Sep 2026 Lab model card

Google DeepMind’s own number for Gemini 4 Argon passed 85% in October 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% Near the ceiling (85%) Gemini 4 Argon Gemini 3.8 Flash Cyber 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Gemini 4 Argon Gemini 3.8 Flash Cyber

Source: Labs’ model cards

One lab put it in a launch post in the last six months

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.

Google DeepMind
DateLaunch postScoreAs the post writes it
Sep 2, 2026 Gemini 3.8 Flash Cyber 71 Real-world vulnerability discovery, internal benchmark across 20 languages

One system card reports it

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
Oct 13, 2026 Gemini 4 Argon system card 86 Real-world vulnerability discovery (internal), historical vulnerabilities discovered 86% (7.1.2) 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%