wity-1 (Wity, reasoning auto)v1.7 · 10 s rule

Data: JevBench v1.8.18, published 2026-11-20 · method v1.7 (10 s rule), re-scored from the recorded per-decision times

Capability 76.9 · API offering, ranked on the API leaderboard

latency 3.0× Jev (v1.5 reference)

Last measured: 2026-10-06 · measurement release: v1.6.1

proprietary hosted API

Base model: undisclosed

intelligence

67.9

calibration

85.9

speed

68.3

cost

58.8

Composite (secondary)

69.0 · Not ranked on this board

Cost and measurement conditions

$0.024 per 1,000 decisions (public list price)

Wity's stated API tariff USD 0.042 per 1M input tokens, output free; measured on the v1.6.1 common cost basis (all items except those outside the Jev reference input range) from this run's token usage

p50 latency: 1.8 s

none (API)

operator's hosted production API, measured as is; API default is off, our request sets reasoning=auto as the operator asked for their main row.

Measured latency over 1,500 decisions: p50 1.847 s · p95 7.970 s

36 decisions over 10 s (36 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.

Breakdowns (not part of the score)

Chance-corrected competence (0 = chance, 100 = perfect) by category on S+P+L1+L2+L3. Raw values, not equated; the same cells feed the compare view.

Capability by subject topic

Rules, policy & law50.4n=1616
Coding & software68.0n=382
Math & numbers52.8n=370
Finance & commerce59.5n=223
Support & operations35.3n=160
Everyday language82.4n=145
Safety & security60.8n=109

Use cases (TypeSafe categories)

Model routing71.3n=524
Legal & compliance67.0n=515
Customer support59.9n=240
E-commerce43.0n=119
Insurance claims45.5n=119
Risk assessment59.0n=118
Financial crime40.5n=101
Feature extraction60.8n=99
Lead generation66.2n=95
Recruiting22.5n=94
Knowledge graphs9.8n=94
LLM guardrails39.7n=93
Moderation71.5n=93
Code linting40.8n=90
Search & retrieval59.3n=90
Science16.9n=90
Advertising33.0n=88
Gaming34.5n=86
Demand forecasting53.0n=83

Cells need at least 30 answered items; † fewer than 30 (indicative only; drawn as hollow, lighter points on the compare radars).

JevBench v1.6.43 values (method v1.6, before the 10 s rule)

Capability 79.12 · Composite 70.77 · rank #22 on the all-systems board · #14 API

intelligence 70.28 · calibration 87.95 · speed 71.79 · cost 58.83

v1.6 speed basis (124 items): p50 1.575 s · p95 4.205 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.

Published source