-
Jinjing Liang, who builds Orca, with a question 6.1 Sol got wrong at its highest setting. The benchmarks above are averages; this is one prompt.
Jinjing Liang
Gpt-6.1-sol max ... it's not very smart. Fails on a logic question
Opus 5.5 medium aces it 🥲
Jinjing Liang's post on X, curated on eChai
eChai Partner Brands
The partnership →