Results

10 results

CyberGym Original results
ProviderModelScoreSourceRegistry No.
SpaceXAIGrok 4.7 (high)80.3%media.x.ai for Grok 4.7 (high) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Model cardSpaceXAISelf-reportedRecord for Grok 4.7 on CyberGym Original40003
SpaceXAIGrok 4.6 (high)79.7%media.x.ai for Grok 4.6 (high) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Model cardSpaceXAISelf-reportedRecord for Grok 4.6 on CyberGym Original40002
Z.aiGLM-5.3 (max)84.5%z.ai for GLM-5.3 (max) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Launch postZ.aiSelf-reportedRecord for GLM-5.3 on CyberGym Original150005
Meta AI (originally Facebook AI Research)Muse Spark (high)43.5%ai.meta.com for Muse Spark (high) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Evaluation reportMetaSelf-reportedRecord for Muse Spark on CyberGym Original80001
Meta AI (originally Facebook AI Research)Muse Spark 1.1 (high)59.0%ai.meta.com for Muse Spark 1.1 (high) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Evaluation reportMetaSelf-reportedRecord for Muse Spark 1.1 on CyberGym Original80002
Z.aiGLM-5.277.2%z.ai for GLM-5.2 on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Launch postZ.aiSelf-reportedRecord for GLM-5.2 on CyberGym Original150004
Meta AI (originally Facebook AI Research)Muse Spark (thinking)43.5%ai.meta.com for Muse Spark (thinking) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Safety reportMetaSelf-reportedRecord for Muse Spark on CyberGym Original80001
AnthropicClaude Opus 4.7 (no thinking)73.1%anthropic.com for Claude Opus 4.7 (no thinking) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Launch postAnthropicSelf-reportedRecord for Claude Opus 4.7 on CyberGym Original20010
Z.aiGLM-5.168.7%z.ai for GLM-5.1 on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Launch postZ.aiSelf-reportedRecord for GLM-5.1 on CyberGym Original150003
Z.aiGLM-5 (thinking)43.2%z.ai for GLM-5 (thinking) on CyberGym Original (opens in a new tab)Vulnerability reproduction successReported Launch postZ.aiSelf-reportedRecord for GLM-5 on CyberGym Original150002