voices
@aiexplained on AI benchmarks
1 quotes from AI researchers about benchmarks, models, and evaluation
"On multiple measures of software engineering, Mythos beats out Opus 4.6 by a massive margin. In SWE-bench Pro for example by 25%."
AI Explained @@aiexplained · 2026-04-08 view on x
SWE-bench Pro Claude Opus 4.6
benchmark.space canonical public ledger of AI capability