BB-Qwen3.5-4B-LoRA (Babak Barazandeh, LoRA on Qwen3.5-4B-Base, hosted /v1/systemone)

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

Capability 60.4 · API offering, ranked on the API leaderboard

registry ranked=false or no composite

Last measured: 2026-10-07 · measurement release: v1.6.1

Licence not stated

Base model: Qwen/Qwen3.5-4B-Basesource

intelligence

38.7

calibration

82.1

speed

81.6

cost

—

Composite (secondary)

— · Not ranked on this board

Cost and measurement conditions

not published (not published)

UNPRICED - NOT A MEASUREMENT FAILURE. The base is disclosed (Qwen/Qwen3.5-4B-Base; reference() resolves it to deepinfra:Qwen/Qwen3.5-4B at 0.03/0.15), but the endpoint reports usage.input_tokens ONLY - no output_tokens on any answer - and the system is API-only, so 'nothing is generated' cannot be verified in its code; the 02 Oct deputy rule keeps an unverified null unpriced. The frozen scorer therefore gives no Cost axis and no composite; the row is reported on Capability. RELEASE-LANE LINE: if the author confirms (or the release lane accepts) a one-pass readout with 0 output tokens, the row prices by one multiplication from the raw at 0.03/M input (receipts/COST-ALTERNATIVES-R59.json).

p50 latency: 0.7 s

none (API)

Hosted full-set API measured 2026-10-07; submitted LoRA checkpoint-030500 on Qwen3.5-4B-Base, weights not released. Serial requests over author ngrok tunnel, no retry; latency includes transit. Complete 1500/1500 answers. Input usage is reported but output usage is absent, so Cost and composite remain unpriced; Capability is reported. Exposure ledger recorded before dispatch.

Published source