INTELLIGENCE BRIEFING · ISSUE 003

SENTIENT WEEKLY

Signal in the AI noise.

A weekly editorial briefing · free in your inbox

— Benchmarks —
GPT-5.5 (xhigh)59.7
GPT-5.5 (medium)56.5
Gemini 3.1 Pro Preview56.4
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)54.9
GPT-5.5 (low)51.5
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)50.5
GPT-5.4 mini (xhigh)50.2
Muse Spark49.9
MiMo-V2.5-Pro49.6
Claude Opus 4.5 (Reasoning)48.8
GPT-5.5 (xhigh)59.7
GPT-5.5 (medium)56.5
Gemini 3.1 Pro Preview56.4
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)54.9
GPT-5.5 (low)51.5
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)50.5
GPT-5.4 mini (xhigh)50.2
Muse Spark49.9
MiMo-V2.5-Pro49.6
Claude Opus 4.5 (Reasoning)48.8