LLM Benchmarks — Scores, Methodology & Live Rankings
What each benchmark measures, how models score, and the current rankings
MMLU-Pro
Knowledge
MMLU-Pro - extended MMLU covering 14 categories with complex reasoning questions.
C-Eval
Knowledge
C-Eval - comprehensive Chinese evaluation benchmark across 52 subjects.
OmniScience Accuracy
Knowledge
OmniScience Accuracy - scientific knowledge accuracy benchmark.
MMLU
Knowledge
MMLU (Massive Multitask Language Understanding) - a benchmark of multitask accuracy across 57 tasks.
Natural Questions
Knowledge
Google Natural Questions - open-domain QA using real user queries from Google Search. 5-shot.
HoVer
Knowledge
HoVer: multi-hop fact verification over claims requiring reasoning over Wikipedia documents, scored as accuracy on a 0-100 scale in Cloudflare's internal Dec...
CMMLU
Knowledge
CMMLU - Chinese multi-task language understanding benchmark; reported in the baidu/ERNIE-5.5-Flash-Base model card evaluation table as CMMLU (EM), 5-shot.
AA-Omniscience Index (public set)
Knowledge
AA-Omniscience Index (public set) - calibrated knowledge index from Aleph Alpha's Omniscience suite, centered at 0 and comparable across models; can be negat...
OmniScience Non-Hallucination
Knowledge
OmniScience Non-Hallucination - scientific knowledge non-hallucination rate benchmark.