Sage 1.3.0 (Levanto Labs)

Data: JevBench v1.6.1, published 2026-10-06

Capability 78.6 · rank #2 of 64

Last measured: 2026-10-05 · measurement release: v1.6.1

proprietary hosted API

Base model: undisclosed

intelligence

65.6

calibration

91.6

speed

93.6

cost

58.2

Composite (secondary)

74.0 · Composite rank #1

Cost and measurement conditions

$0.025 per 1,000 decisions (estimated)

Levanto list tariff, top tier: USD 0.05 per 1M input tokens, USD 10 per 1M output tokens (https://levanto.ai/pricing, read 5 Oct 2026)

p50 latency: 0.2 s

none (API)

Levanto hosted API, text only, measured from Sandy (Helsinki) on 5 Oct 2026; full set 1,200 sealed + P300 (v1.6.1); not evaluated on ImageJevBench.

Published source