ai benchmark - Sean Kim — Arts and Tech

March 27, 2026

Published by Sean Kim on March 27, 2026

Mistral Small 4 Review: How the 119B MoE Open-Source Model Matches GPT-OSS 120B at 40% Lower Latency

The open-source AI landscape just shifted dramatically. On March 16, 2026, Mistral AI dropped Mistral Small 4 — a 119B parameter Mixture of Experts model under […]

March 15, 2026

Gemini 3.1 Pro ARC-AGI-2 benchmark 77.1 percent score visualization

Published by Sean Kim on March 15, 2026

Gemini 3.1 Pro Scores 77.1% on ARC-AGI-2: How Google Retook the AI Crown with a 2X Reasoning Leap

Gemini 3.1 Pro ARC-AGI-2 results are in — and they’re rewriting the AI leaderboard. Google’s latest flagship model just scored 77.1% on the notoriously difficult ARC-AGI-2 […]

January 12, 2026

Published by Sean Kim on January 12, 2026

Google Gemini 3.5 Preview: Snow Bunny Leak Reveals Ultra Model with 3,000-Line Code Generation and Deep Think Reasoning

While CES 2026 dominates the headlines with flashy hardware announcements, the real earthquake in AI is happening behind closed doors at Google. Leaked benchmark data from […]