Duplicate Link Repost of Kimi K3.1 Pro xdev-bench-hard Benchmark Tweet
ricklamers · x · 2026-10-24
This post is ricklamers' link repost of his own tweet about Kimi K3.1 Pro's xdev-bench-hard results, with the BenchLM page text attached. All information duplicates the original post and its chart: xdev-bench-hard is Moonshot's internal source-code-based vulnerability exploitation benchmark, where Kimi K3.1 Pro leads at 81% pass@3, with the platform noting the score is a provider self-report shown for reference only. No new information.
More from Models
- Kimi k3.1's 'ridiculously bad' usage limits overshadow a strong model — haider1 · 2026-10-24
- Users Report Gemini Severely Hallucinating and Unusable for Days — PsychBreacher · 2026-10-24
- Muse's invisible-messages bug: tool-call progress never renders, Meta silent for 36 hours — inductionheads · 2026-10-24
- Kimi K3.1 Pro Jumps to 81% pass@3 on Cyber Exploit Benchmark, Up From K3's 33% — ricklamers · 2026-10-24
- LisanBench Token Efficiency: Anthropic and Muse Wonder Lead Tokens per Step — scaling01 · 2026-10-24
- AI-Assisted Paper on Z-Library Cites a TorrentFreak Article That Doesn't Exist — TangerineDream · 2026-10-24