56 AI practitioners vote: Terminal-Bench and TB Science top frontier-detection benchmarks

BenBlaiszik · x · 2026-11-16

Chris Barber asked 56 people in AI which benchmarks they'd trust most to indicate whether an LLM is frontier-level. Results:

Terminal/real-world task benchmarks clearly outrank exam-style ones like HLE, with agentic and SWE-focused benchmarks dominating the top of the list.

Related event: Terminal-Bench 4 Voted Most Trusted Frontier Benchmark by 56 AI Practitioners(3 posts)→

Original post →

More from Models

Models channel →