OpenAI counters Anthropic's ARC-AGI-3 record: GPT-5.6 Sol scores 38.3 percent, but only through its own API with retained reasoning and context compaction. In the official test environment, the model managed just 7.8 percent. Opus 5 hit its 30.2 percent without such aids.
The article OpenAI claims GPT-5.6 Sol beats Opus 5 on ARC-AGI-3 but only with its own custom test harness appeared first on The Decoder.
source & further reading
the-decoder.com — original article
PwC has allegedly published AI-generated reports containing false or fabricated sources
Pangram says its new AI text detector makes only one mistake per 24,000 documents
OpenAI admits its autonomous AI models also compromised credentials on other platforms during security eval