Image JevBench v0.1.5 · individual system
Autoloops – Gemma 4 31B IT
Closed APIBase model: undisclosedArchived v0.1.5 score, not ranked on the v0.3 scale. See the v0.1.5 archive.
the operator's hosted API
Image JevBench v0.1.5 composite score
47.138
v0.1.5 rank #32 of 50 (archived).
From the published full-benchmark aggregate. The composite combines intelligence, calibration, speed and cost.
Published axes
- intelligence
- 79.3
- calibration
- 82.4
- speed
- 73.9
- cost
- 42.6
Cost and speed evidence
- Cost per 1,000 decisions
- USD 0.081611
- Cost basis
- Autoloops published Gemma 4 31B token rates applied to returned usage receipts
- Measured latency · p50 / p95
- 1.425 s / 2.868 s
- Adjusted latency · p50 / p95
- 1.425 s / 2.868 s
- Latency adjustment
- none (hosted API, measured as is)
- Public accuracy
- 84.6%
- Sealed accuracy
- 87.1%
Published 2026-10-01. Scores and ranks can change in a later release. See the method notes.