LLM Benchmarks — Scores, Methodology & Live Rankings

What each benchmark measures, how models score, and the current rankings

Reset

Most tested benchmarks

Ranked by how many models have tracked scores — open a benchmark for its full live ranking.

$OneMillion-Bench 11 models tested · latest result 28.08.2026 68.1% HealthBench 6 models tested · latest result 18.08.2026 60.2% PLawBench 5 models tested · latest result 18.08.2026 73.2% PRBench-Finance 5 models tested · latest result 18.08.2026 58.3% PRBench-Legal 5 models tested · latest result 18.08.2026 57.6% HealthBench Consensus 2 models tested · latest result 08.08.2025 89.9% HealthBench Hard 2 models tested · latest result 08.08.2025 30% ACOS 2 models tested 33.3% POP909-CL 2 models tested 15.8%

PLawBench

General Capabilities

PLawBench - professional law benchmark. Evaluated using gemini-3.1-pro-preview.

Active View →

PRBench-Legal

General Capabilities

PRBench-Legal - professional reasoning benchmark for legal domain. Evaluated using gemini-3.1-pro-preview.

Active View →

PRBench-Finance

General Capabilities

PRBench-Finance - professional reasoning benchmark for finance domain. Evaluated using gemini-3.1-pro-preview.

Active View →

$OneMillion-Bench

General Capabilities

$OneMillion-Bench - expert score. Evaluated using gemini-3.1-pro-preview.

Active View →

HealthBench Consensus

General Capabilities

HealthBench Consensus - a subset of HealthBench validated by the consensus of multiple physicians.

Active View →

HealthBench Hard

General Capabilities

HealthBench Hard - a challenging subset of HealthBench conversations testing realistic health conversations with individuals and health professionals.

Active View →

POP909-CL

General Capabilities

POP909-CL: classification variant over the POP909 piano-performance dataset, scored as accuracy on a 0-100 scale in Cloudflare's internal Decision Index 0.2....

Active View →

ACOS

General Capabilities

ACOS: aspect-category-opinion-sentiment quad classification over reviews, scored as per-review F1 on a 0-100 scale in Cloudflare's internal Decision Index 0....

Active View →

HealthBench

General Capabilities

HealthBench - healthcare-related benchmark evaluating medical knowledge and reasoning.

Active View →