Vulnerability Exploitation on CVEBench One-Day
26.1Pass@1Seed Agent
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Seed AgentBackbone=Kimi-K2.52026.05 | 26.1 | 34.5 | 37.5 | — | — | — | — | — | — | |
| Seed AgentBackbone=DeepSeek-V3.12026.05 | 16.9 | 24.8 | 27.5 | — | — | — | — | — | — | |
| Seed AgentBackbone=Qwen3-235B2026.05 | 16.8 | 24.2 | 27.5 | — | — | — | — | — | — | |
| Seed AgentBackbone=MiniMax-M2.52026.05 | 15.8 | 24.6 | 30 | — | — | — | — | — | — | |
| ACEBackbone=DeepSeek-V3.12026.05 | — | — | — | 20 | -7.5 | — | — | — | — | |
| ACEBackbone=Kimi-K2.52026.05 | — | — | — | 35 | -2.5 | — | — | — | — | |
| ACEBackbone=MiniMax-M2.52026.05 | — | — | — | 22.5 | -7.5 | — | — | — | — | |
| ACEBackbone=Qwen3-235B2026.05 | — | — | — | 22.5 | -5 | — | — | — | — | |
| CyAgentBackbone=DeepSeek-V3.12026.05 | — | — | — | — | — | — | — | 12.5 | — | |
| CyAgentBackbone=Kimi-K2.52026.05 | — | — | — | — | — | — | — | 30 | — | |
| CyAgentBackbone=MiniMax-M2.52026.05 | — | — | — | — | — | — | — | 25 | — | |
| CyAgentBackbone=Qwen3-235B2026.05 | — | — | — | — | — | — | — | 20 | — | |
| CyberEvolverBackbone=DeepSeek-V3.12026.05 | — | — | — | — | — | 32.5 | 5 | — | — | |
| CyberEvolverBackbone=Kimi-K2.52026.05 | — | — | — | — | — | 45 | 7.5 | — | — | |
| CyberEvolverBackbone=MiniMax-M2.52026.05 | — | — | — | — | — | 40 | 10 | — | — | |
| CyberEvolverBackbone=Qwen3-235B2026.05 | — | — | — | — | — | 32.5 | 5 | — | — | |
| T-AgentBackbone=DeepSeek-V3.12026.05 | — | — | — | — | — | — | — | — | 20 | |
| T-AgentBackbone=Kimi-K2.52026.05 | — | — | — | — | — | — | — | — | 37.5 | |
| T-AgentBackbone=MiniMax-M2.52026.05 | — | — | — | — | — | — | — | — | 32.5 | |
| T-AgentBackbone=Qwen3-235B2026.05 | — | — | — | — | — | — | — | — | 22.5 |