safety benchmark
Google Real-world Vulnerability Discovery is an internal benchmark covering more than 1,200 recent confirmed vulnerabilities in popular open-source projects across 20 programming languages.
Updated Sep 5, 2026
Higher score ranks better on this benchmark.
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score71.00% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
The leading models and scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What Google Real-world Vulnerability Discovery measures and how its scores work.
Google Real-world Vulnerability Discovery is Google's internal vulnerability-discovery benchmark.
It measures recall across more than 1,200 recent confirmed vulnerabilities in popular open-source projects spanning 20 programming languages, using the Score metric as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about Google Real-world Vulnerability Discovery.
Gemini 3.8 Flash Cyber is currently ranked first with 71.00%.
The current leaders are Gemini 3.8 Flash Cyber (71.00%).
No matched official input price is currently available.
No matched runtime record is currently available.
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
It measures recall across more than 1,200 recent confirmed vulnerabilities in popular open-source projects spanning 20 programming languages, using the Score metric as a ratio.
Yes. Higher values rank better for this benchmark.
1 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.
Ranking basisThis google real-world vulnerability discovery AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
Gemini 3.8 Flash Cyber currently leads Google Real-world Vulnerability Discovery with 71.00%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.