log inget an API key
Platform benchmark

claude-fable-5-2

anthropic · GPQA-Diamond · seed 42 · 2026-11-11 05:04 UTC

ResultsGPQA-Diamond · n=96 · seed 42
96.9%

96.9% correct · 97.9% answered on GPQA-Diamond

Score per $
0.37
Run cost
$2.63
Latency p50
6.9 s
Latency p95
17.0 s
Items
96/96 completed
Dropped
0

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