Expired50% confidenceBenchmarkExact time
On XBOW's 104-question challenge set XBEN using gpt-5.5, T3MP3ST black-box single-agent achieved a pass@1 of 90.1%, with the worst single-round scan at 87.5% (91/104), surpassing XBOW's previously self-reported 85%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/6/2026
First Seen
Valid until: 10/4/2026(expired)
Sources
T3MP3ST: The Open-Source Framework That Turns Coding Agents into Autonomous Red Team Operators
twitterelder_plinius7/5/2026
Related Claims
UnverifiedIn XBEN white-box mode, T3MP3ST's pass@1 reached 98.7%, with the worst single round at 98.1% (102/104).76% similarUnverifiedThe MTP-LX 4-bit version scored 55 out of 100 on a financial planning reasoning task as rated by GPT-5.5 Thinking, while GPT-5.5 Pro scored 82 on the same question.62% similarUnverifiedThe 50 TOPS computing power of the XDNA 2 NPU exceeds the 40 TOPS threshold for Microsoft Copilot+ PC certification.61% similarUnverifiedMuse Glimmer 30B is reported to achieve 74.9 tokens per second on an RTX 5090, and reviewers observed approximately 60–65 tokens/sec running the full-precision version on an RTX 3090.61% similarUnverifiedOn the 40-task academic benchmark Cybench using Opus 4.8 (with hints and solutions removed), T3MP3ST achieved a single-attempt hint-free pass@1 of 23/40 = 58%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/114274API
curl https://kongchang.com/api/v1/knowledge/claims/114274MCP
get_claim(id=114274)