LiveBenchReasoning
48.91/ 100
Verified
Last Verified: 2026-02-20LiveBench
Contamination-free, continuously updated reasoning benchmark.
Beta version: *Information might not be fully accurate. Please report any discrepancies.
Beta version: *Information might not be fully accurate. Please report any discrepancies.
Latest Data
2026-02-20
Context Window
512k
tokens
Input Cost
$1.75
per 1M tokens
Output Cost
$14.00
per 1M tokens
Cache Cost
$0.13 / Free
read / write per 1M
Parameters
Ultra-High Dense
model footprint
2 Variants Available
Performance Analysis // Verified Benchmarks
Contamination-free, continuously updated reasoning benchmark.
A more robust and harder version of MMLU, focusing on complex reasoning and STEM subjects.
Humanity's Last Exam - Hard reasoning benchmark without tools.