Bosun v3.1 0.6B

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

Capability 39.4 · Not ranked in the current release

Last measured: 2026-09-29 · measurement release: v1.5.3

apache-2.0, not gated; LICENSE + NOTICE (Clause Logic Inc.) present at the pinned revision

Base model: Qwen/Qwen3-0.6Bsource

intelligence

13.6

calibration

65.2

speed

61.8

cost

77.5

Composite (secondary)

2.5 · Not ranked on this board

Cost and measurement conditions

$0.0056 per 1,000 decisions (estimated)

ESTIMATE: documented hosted-model estimate; no exact base-model floor applies. $0.01/M input, $0/M output; same-base frozen raw-qwen3-0.6b estimate.

p50 latency: 4.0 s

x2 + 0.15 s (assumption, not measured)

evaluator-owned CPU, Sandy (AMD Ryzen 5 3600), 4 of 12 threads, nice -n 5, shared host, offline (HF_HUB_OFFLINE=1, local_files_only=True), credential-free (no API key, no HF token)

Published source