Muse Spark 1.3

NewMuse Spark 1.3

Ranks #11 of 35 on reading real contracts into structured billing data, -3.2 pts vs GPT-5.5.

72.8%

Accuracy

#11 of 35

5.2%

Hallucination

HIGH-confidence & wrong

$48.9

Cost / 1k contracts

$0.05 each · via OpenRouter

32.6s

Median latency

p90 44.1s

±0

Run-to-run σ

1 runs

1.49

Value

acc. pts per $/1k

Tokens per contract

Input21,982

Output5,045

Reasoning2,106

Reliability 100% · valid structured output across 30 calls.

Want the full picture? How we score