INTELLIGENCE BRIEFING · ISSUE 003

SENTIENT WEEKLY

Signal in the AI noise.

A weekly editorial briefing · free in your inbox

— Benchmarks —
GPT-5.5 (xhigh)65.6
GPT-5.5 (medium)61.5
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)60.4
Claude Opus 4.7 (Non-reasoning, High Effort)58.8
Gemini 3.1 Pro Preview58.3
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)55.7
GPT-5.5 (low)52.7
MiMo-V2.5-Pro51.5
Muse Spark51.5
DeepSeek V4 Pro (Reasoning, High Effort)51.2
GPT-5.5 (xhigh)65.6
GPT-5.5 (medium)61.5
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)60.4
Claude Opus 4.7 (Non-reasoning, High Effort)58.8
Gemini 3.1 Pro Preview58.3
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)55.7
GPT-5.5 (low)52.7
MiMo-V2.5-Pro51.5
Muse Spark51.5
DeepSeek V4 Pro (Reasoning, High Effort)51.2