VQV Signal
According to a post on X by @mercor, Kimi K3.1 Pro scored 65.5% on the APEX-Agents leaderboard, placing second among open-weight models. It trails DeepSeek-V4.1-Flash at 69.8% and ranks ahead of Qwen 3.8-Max at 63.3%. Mercor says the Kimi family gained nearly 30 points on the benchmark in five months.
According to a post on X by @mercor, Kimi K3.1 Pro scored 65.5% on the APEX-Agents leaderboard, placing second among open-weight models. It trails DeepSeek-V4.1-Flash at 69.8% and ranks ahead of Qwen 3.8-Max at 63.3%. Mercor says the Kimi family gained nearly 30 points on the benchmark in five months.
AI-assisted summary based on the listed source.
Mercor's APEX-Agents leaderboard puts Kimi K3.1 Pro at 65.5%, behind DeepSeek-V4.1-Flash at 69.8% and ahead of Qwen 3.8-Max at 63.3%. Mercor says the Kimi family gained nearly 30 points on the benchmark in five months. Why it matters: Teams building agents on open models get another independent ranking to choose...
Developers choosing open models for agent work get another ranking to compare, though it comes from a single benchmark run by Mercor. Teams should check whether APEX-Agents matches their own tasks before changing models. Watch for later leaderboard updates to see whether these positions hold.
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.
