Image JevBench v0.1.5 · individual system
GPT-5.6 Luna
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
11.048
v0.1.5 rank #45 of 50 (archived).
From the published full-benchmark aggregate. The composite combines intelligence, calibration, speed and cost.
Published axes
- intelligence
- 91.8
- calibration
- 95.8
- speed
- 62.6
- cost
- 23.5
Cost and speed evidence
- Cost per 1,000 decisions
- USD 0.352365
- Cost basis
- OpenRouter usage.cost receipts
- Measured latency · p50 / p95
- 2.878 s / 19.176 s
- Adjusted latency · p50 / p95
- 2.878 s / 19.176 s
- Latency adjustment
- none (hosted API, measured as is)
- Public accuracy
- 92.5%
- Sealed accuracy
- 95.6%
Published 2026-10-01. Scores and ranks can change in a later release. See the method notes.