Benchmark Almanac

Gemini 3.8 Flash Cyber

Gemini 3.8 Flash Cyber.

Google DeepMind Released September 2nd, 2026 Family Gemini 3.8 The lab's model card Compare with others
3
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Google DeepMind Sep 2026

Gemini 3.8 Flash Cyber

Closed weights Mid-size

No Epoch Capabilities Index score yet
  • CyberGym 86.3% #8 /34

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Safety and security

BenchmarkScoreRankSource
CyberGym 86.3% #8 of 34 Official leaderboard
CWE-bench 47.2% #3 of 3 Lab model card
Real-world vulnerability discovery 71% #2 of 2 Lab model card

Its lab's number next to a leaderboard

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark Lab says Board says Gap
CyberGym 86.2% CyberGym Pass@1, vulnerability discovery in C/C++ 86.3% Leaderboard, Google Antigravity Same

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.