Jebadiah 9B v2.1 (Frontier Infra, Qwen3.5-9B LoRA)
Data: JevBench v1.6.39, published 2026-10-22
Capability 63.4 · rank #43 of 139 on the open-weights board
Last measured: 2026-10-16 · measurement release: v1.6.25
Apache-2.0 (weights and base)
intelligence
37.2
calibration
89.7
speed
91.4
cost
48.9
Composite (secondary)
30.3 · Composite rank #67
Cost and measurement conditions
$0.051 per 1,000 decisions (estimated)
ESTIMATE (*est.), base-model market reference through the frozen pricing_v15 module: declared base Qwen/Qwen3.5-9B -> qwen/qwen3.5-9b USD 0.09999999999999999/M input, USD 0.15/M output. Estimated, not charged, not a quote from the author or any host. Frozen pricing_v15: base-model references unchanged since sha256 533d80f0...d960e5, the module this row was first priced with (the later re-freezes only add hosted-API launch-list keys), USD per 1,000 decisions over the common 1,485-item cost basis (the 15 very long items are left out of cost for every row; refused items cost nothing and still count as wrong answers). Tokens as reported by the author's own server (750,303 input over the 1,485 answered items, output_tokens 1 per answered request). COMMON COST BASIS (v1.6.30): cost per 1,000 decisions is computed on the common 1,485 items of this draw, leaving out the 15 very long items (at least 76,358 input tokens as counted by the rows that answered them). They are the 15 items the Jev reference refused with max_tokens_exceeded, which the other rows that did not answer them refused or failed on; their tokens count for no row, whether the row refused or answered them, and a refused item still counts as a wrong answer for Intelligence. This row: USD 0.050675 per 1,000 decisions (0.785x the official cost cap USD 0.064595), against USD 0.050169 over all 1,500 items (v1.6.29).
Measured p50 latency: 0.043 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: 0.24 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.043 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 = 0.24 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
Evaluator-owned rented Lium GPU pod (measurement receipts on file), 1x NVIDIA GeForce RTX 5090 32 GB (sm_120, driver 595.71.05), Romania (EU) - different hardware from the RTX PRO 6000 the author measures on, so Speed is a lower bound on this card and not comparable to their 49.9 ms median. The author's OWN standalone server `jebadiah-serve --model <pinned local dir> --device cuda` from getainode/jebadiah @ 74a0cd92965529e90a411532e9887b544c931b2d (the commit behind the published jebadiah-27b row, independently code-reviewed PASS), installed from the author's own frozen uv.lock (`uv sync --frozen --no-dev --extra cuda`, torch 2.14.0+cu130, transformers 5.17.0, flash-linear-attention 0.5.2), all author defaults (dtype auto = bf16, batch-size 8, --max-prompt-tokens 8192, strict prompt-contract check ON, the repo's own temperatures.json, fp32 candidate logits), JEBADIAH_API_KEY unset. Isolation: server started inside a network namespace with loopback only (unshare -n), the cut proven before the sealed input was staged and re-proven immediately before the first sealed request, synthetic smoke gate passed in between; runner unchanged (run_v15.py, 0 resumes, rc 0); one use of input-selfhosted-1500 (custody #20323, deputy #20315). Pod removed by exact id and verified gone four ways. Published Speed uses the standing x2 + 0.15 s self-hosted adjustment; raw p50 0.0502 s / p95 0.0837 s.