@SemiAnalysis_ Real-work benchmarks that last hours expose the gap. Closing it will need more continuous GPU time, not j | Hanami
@SemiAnalysis_ Real-work benchmarks that last hours expose the gap. Closing it will need more continuous GPU time, not just better scores.
Reply to @SemiAnalysis_: Today we’re releasing GDPx, a benchmark for measuring agentic capabilities across the most valuable domains.
GDPx is a true frontier-level benchmark: even the best model scores just 12% (1/7)🧵