log inget an API key
Platform benchmark

deepseek-v4-flash-0731

deepseek · GPQA-Diamond · seed 42 · 2026-11-10 06:09 UTC

ResultsGPQA-Diamond · n=96 · seed 42
89.6%

89.6% correct · 95.8% answered on GPQA-Diamond

Score per $
5.35
Run cost
$0.17
Latency p50
14.0 s
Latency p95
305.1 s
Items
96/96 completed
Dropped
0

Dataset: GPQA-Diamond · question and response text withheld under dataset access terms.