INTELLIGENCE BRIEFING · ISSUE 003

SENTIENT WEEKLY

Signal in the AI noise.

A weekly editorial briefing · free in your inbox

— Benchmarks —
GPT-5.5 (Xhigh)56.7
GPT-5.5 (Medium)52.6
DeepSeek V4 Pro 0813 (Max)52.4
Claude Opus 4.7 (Non-reasoning, High)52.3
DeepSeek V4 Flash 0731 (Max)51.7
Gemini 3.1 Pro Preview49.3
GPT-5.5 (Low)45.8
Muse Spark45.0
DeepSeek V4 Flash (Reasoning, High Effort)44.8
MiMo-V2.5-Pro (Reasoning)43.1
GPT-5.5 (Xhigh)56.7
GPT-5.5 (Medium)52.6
DeepSeek V4 Pro 0813 (Max)52.4
Claude Opus 4.7 (Non-reasoning, High)52.3
DeepSeek V4 Flash 0731 (Max)51.7
Gemini 3.1 Pro Preview49.3
GPT-5.5 (Low)45.8
Muse Spark45.0
DeepSeek V4 Flash (Reasoning, High Effort)44.8
MiMo-V2.5-Pro (Reasoning)43.1