PLPramaana

Anthropic

Claude Sonnet 5

Release date: 6/30/2026

A balanced frontier model designed for high-volume professional deployments.

Pramaana IndexAccuracy: StrongLatency: StrongCost: Strong
Accuracy / Pramaana Index
68.61%± 0.99
Latency / Pramaana Index
424.52s
Cost / Test / Pramaana Index
$1.85
Context window
500k
Max output tokens
96k
Input modality
Text · Image · File
Hyperparameter settings

temperature: 0.0

reasoning: extended

fallbacks: disabled

Benchmark performance for Claude Sonnet 5

BenchmarksAccuracyRanking
Pramaana Index68.61% ± 0.994 / 35
Pramaana Multimodal Index64.53% ± 1.166 / 24
Legal Research Fidelity66.41% ± 1.333 / 18
Financial Modeling Agent58.72% ± 1.505 / 22
Clinical Documentation Safety62.31% ± 1.674 / 19
MATH-50076.41% ± 0.486 / 112
GPQA Diamond80.42% ± 0.656 / 121
MMLU-Pro77.91% ± 0.825 / 119
Adaptive Tutoring Dialogue64.21% ± 0.995 / 16
SWE-bench Verified59.62% ± 1.164 / 69
LiveCodeBench76.53% ± 1.334 / 127
Agentic Reliability52.73% ± 1.506 / 12
Strategic Games Arena60.82% ± 1.675 / 20
Benefits Navigator64.12% ± 0.485 / 16

License: Proprietary · Evaluation settings, model endpoints, and benchmark versions are frozen with each published run.

Read our methodology