Llama 4 Scout

NewLlama 4

Ranks #42 of 43 on reading real contracts into structured billing data — -36.5 pts vs GPT-5.5.

32.8%

Accuracy

#42 of 43

37.4%

Hallucination

HIGH-confidence & wrong

$2.60

Cost / 1k contracts

$0.00 each · via OpenRouter

42.2s

Median latency

p90 61.5s

±11.2

Run-to-run σ

3 runs

12.67

Value

acc. pts per $/1k

Tokens per contract

Input20,659

Output1,746

Reasoning0

Reliability 100% · valid structured output across 18 calls.

Want the full picture? How we score →