MMLU-Pro

Healthy

1.0 · University of Waterloo · general

Massive multitask language understanding with harder, reasoning-focused questions.

Reviewed results

Model	Score	Date	Provenance	Source
Llama 4	84.0%	2026-07-01	Vendor-run	Evidence
Claude Mythos 5	87.0%	2026-07-01	Vendor-run	Evidence
GPT-5.6 Sol	88.0%	2026-07-01	Vendor-run	Evidence