log inget an API key
Platform benchmark

deepseek-v4.1-flash-1017

deepseek · GPQA-Diamond · seed 42 · 2026-11-10 06:32 UTC

ResultsGPQA-Diamond · n=96 · seed 42
92.7%

92.7% correct · 99.0% answered on GPQA-Diamond

Score per $
2.95
Run cost
$0.31
Latency p50
18.1 s
Latency p95
294.6 s
Items
96/96 completed
Dropped
0

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