Vals AI
CyberBench v1.1
Can autonomous agents craft PoC inputs that trigger OSS-Fuzz vulnerabilities—and produce source patches that fix them?
ModelsModels with a result.48
Top-3 spreadPoints from first to third.2.5 pts
UpdatedDate the source changed the results.5 Nov 2026
Result and cost
48 of 48 results
Results
48 results#ModelResultThe score from the source.CostUS dollars to run one task.TimeTime to run one task.