Claude Opus 5

NewClaude 5

Ranks #2 of 35 on reading real contracts into structured billing data, +1.8 pts vs GPT-5.5.

77.8%

Accuracy

#2 of 35

3.6%

Hallucination

HIGH-confidence & wrong

$370

Cost / 1k contracts

$0.37 each · via OpenRouter

71.2s

Median latency

p90 89.6s

±0

Run-to-run σ

1 runs

0.21

Value

acc. pts per $/1k

Tokens per contract

Input36,515

Output7,478

Reasoning0

Reliability 100% · valid structured output across 30 calls.

Want the full picture? How we score