BAAI bge-reranker-v2-m3
Data: JevBench v1.6.1, published 2026-10-06
Capability 44.1 · rank #63 of 92 on the open-weights board
Last measured: 2026-10-02 · measurement release: v1.6.1
Apache-2.0
intelligence
0.1
calibration
88.1
speed
93.9
cost
59.3
Composite (secondary)
0.0 · Composite rank #125
Cost and measurement conditions
$0.023 per 1,000 decisions (estimated)
v1.5.4 published cost per 1,000 decisions carried (pricing rules unchanged; v1.6 item lengths differ): ESTIMATE: base-model market reference (deepinfra:BAAI/bge-m3)
Measured p50 latency: 0.017 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: 0.18 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.017 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 = 0.18 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
evaluator-owned Lium GPU pod (A6000), offline read-only container