Amos 1 large (Scira)v1.7 · 10 s rule
Data: JevBench v1.8.7, published 2026-11-03 · method v1.7 (10 s rule), re-scored from the recorded per-decision times
Capability 78.0 · API offering, ranked on the API leaderboard
cost 6.6× Jev (v1.5 reference)
Last measured: 2026-10-13 · measurement release: v1.6.17
Apache-2.0 open weights declared by the submitter (mukaddamzaid/amos-1-large); the measured object is Scira's hosted endpoint, whose deployed weights were not inspected
intelligence
68.2
calibration
87.8
speed
83.3
cost
30.0
Composite (secondary)
20.3 · Not ranked on this board
Cost and measurement conditions
$0.215 per 1,000 decisions (estimated)
ESTIMATE (*est.), exact base-model market reference from the frozen 25 Sep 2026 snapshot (pricing_v15 sha256 dae86740...): qwen/qwen3.8-27b USD 0.42/M input, USD 3.0/M output, x the provider-reported input tokens; free keyless endpoint, nothing generated (output 0). OVER THE OFFICIAL COST CAP, DISCLOSED: USD 0.214623 per 1,000 decisions on the common basis (USD 0.542843 over all 1,500 items) is 3.323x the official cap USD 0.064595; the row is ranked (v1.6.16 vllm-sr-d3 precedent) and falls outside the official-caps board views by construction. 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 0.214623 per 1,000 decisions (3.323x the official cost cap USD 0.064595), against USD 0.542843 over all 1,500 items (v1.6.29).
p50 latency: 0.5 s
none (API)
Vendor-hosted api.amos.scira.ai /v1/systemone API, model `amos-1-large`; latency measured from Sandy (Germany) on the official per-item latency subset without API adjustment. Full S1200+P300 draw of v1.6-regular-20261012 through the unchanged run_api_full_v161.py; the full-set exposure gate logged all 1,200 sealed items to provider `scira` before the first request (every sealed item of this draw was already retired). Native probabilities on all three question types, no generated tokens. Hosting implementation and deployed weights were not independently inspected. Free, keyless; 1 s spacing for the documented 60 requests/minute.
Measured latency over 1,500 decisions: p50 0.532 s · p95 0.885 s
21 decisions over 10 s (21 of them answered without error, counted as wrong).
A decision that takes longer than 10 seconds (measured time) counts as a wrong answer and as zero calibration for that item: each type's calibration is multiplied by the share of its decisions answered within 10 s. The limit uses the measured time (raw). The displayed adjusted time for self-hosted rows (2 × + 0.15 s) is an assumption and is not used for the limit.
JevBench v1.6.43 values (method v1.6, before the 10 s rule)
Capability 79.36 · Composite 20.40 · rank #130 on the all-systems board · #35 API
intelligence 69.72 · calibration 88.99 · speed 83.62 · cost 30.05
v1.6 speed basis (124 items): p50 0.509 s · p95 0.854 s
These figures are kept for comparison. The current figures above are re-scored under the 10 s rule from the recorded per-decision times and replace them.