Manchego v2.1
Data: JevBench v1.6.1, published 2026-10-06
Capability 58.3 · rank #40 of 92 on the open-weights board
Last measured: 2026-10-04 · measurement release: v1.6.1
Apache-2.0 (code and weights, author-declared)
intelligence
32.5
calibration
84.0
speed
90.7
cost
64.3
Composite (secondary)
24.5 · Composite rank #53
Cost and measurement conditions
$0.015 per 1,000 decisions (estimated)
v1.5.4 published cost per 1,000 decisions carried (pricing rules unchanged; v1.6 item lengths differ): ESTIMATE: frozen 25 Sep DeepInfra Qwen/Qwen3.5-4B market reference, already marked deprecated at that cutoff (replaced by Qwen/Qwen3.5-9B). $0.03/M input, zero generated output; 836,500 measured input tokens across 1,624 decisions. Frozen v1.5 base-model floor applied; no bookable Manchego tariff claimed. Re-score if the basis changes.
Measured p50 latency: 0.054 s (on-GPU, no network, loopback; not directly comparable with API latency, which we time end to end from our measuring host, network included)
Ranking and cap use: 0.26 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.054 s on-GPU, no network (timed on our GPU over loopback). Not directly comparable with API latency, which we time end to end from our measuring host, network included. The ranking and latency cap use the same estimate for every self-hosted row: 2 × measured + 150 ms = 0.26 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
evaluator-owned offline RTX6000 GPU