log inget an API key
Platform benchmark

deepseek-v4.1-flash

deepseek · GPQA-Diamond · seed 42 · 2026-10-01 06:14 UTC

ResultsGPQA-Diamond · n=96 · seed 42
78.1%

78.1% correct · 100.0% answered on GPQA-Diamond

Score per $
7.74
Run cost
$0.10
Latency p50
20.3 s
Latency p95
79.8 s
Items
96/96 completed
Dropped
0

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