Solar Pro 4's AA-Omniscience score improves from -53 to -1, however the improvem

• benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.

A model can post a large honesty-benchmark gain simply by answering less: Solar Pro 4's accuracy stays near 19% while its attempt rate more than halves, so check attempt rates before reading such scores as knowledge.

• postCoding Agent Index: Sonnet 5.5 leads on score, GPT-6.1 Sol wins on cost
• postGPT-6.1 Sol sets a new cost-efficiency frontier on Intelligence Index
• postSafety blocks hit defensive cyber work: CyberGym results and costs
• postSolar Mini 4: cheap tokens, expensive tasks, weak agentic coding

• postKorean AI lab Upstage has released Solar Pro 4, scoring 42 on the Artificial…Artificial Analysis
• postAA-Omniscience regresses 10 points from Qwen3.7 Max (+14 to +4), reversing its…Artificial Analysis
• postMuse Spark 1.2 continues Meta's AA-Omniscience pattern: the score rose from 18…Artificial Analysis

Checking sign-in…

Loading comments…