Fastino GLiNER-2.5-Decide (hosted API)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 34.6 · API offering, ranked on the API leaderboard

Last measured: 2026-10-05 · measurement release: v1.6.1

proprietary hosted API

Base model: fastino/gliner2-large-v1source 1source 2 · Measured via Fastino's hosted API. A 340M English classifier (8k context), not built for multi-step reasoning: near chance on Noul and Score items; 23 very long items exceed its context. Our request follows Fastino's documented format. The open checkpoint scores 11.2 on the community Decision Index (rank 53 of 70; Jev 57.9). Fastino's larger GLiDE is a separate model, ranked separately on the API board.

intelligence

7.0

calibration

62.1

speed

85.0

cost

45.8

Composite (secondary)

0.3 · Not ranked on this board

Cost and measurement conditions

$0.064 per 1,000 decisions (not published)

ESTIMATE: published Fastino sources conflict (USD 0.03/M vs 0.15/M input); conservative higher USD 0.15/M input, 0/M output x measured tokens; no invoice

p50 latency: 0.4 s

none (API)

external hosted API (Fastino); received the full set: 1,200 sealed + 300 public items (v1.6.1)

Measured latency over 1,500 decisions: p50 0.420 s · p95 0.755 s

0 decisions over 10 s.

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 & law0.0n=1611
Coding & software1.6n=382
Math & numbers0.0n=370
Finance & commerce0.0n=221
Support & operations0.0n=158
Everyday language12.5n=145
Safety & security0.0n=109

Use cases (TypeSafe categories)

Model routing6.3n=524
Legal & compliance0.0n=515
Customer support0.0n=238
E-commerce0.0n=119
Insurance claims0.0n=119
Risk assessment1.0n=117
Financial crime0.0n=100
Feature extraction0.0n=98
Lead generation0.0n=93
Recruiting1.0n=94
Knowledge graphs0.0n=94
LLM guardrails13.3n=91
Moderation0.0n=93
Code linting0.0n=90
Search & retrieval0.0n=90
Science0.0n=90
Advertising0.0n=88
Gaming0.0n=86
Demand forecasting0.0n=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 34.57 · Composite 0.34 · rank #208 on the all-systems board · #44 API

intelligence 7.01 · calibration 62.13 · speed 84.71 · cost 45.82

v1.6 speed basis (124 items): p50 0.441 s · p95 0.768 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