Image JevBench v0.3.0 · individual system
GPT-6 Luna via OpenAI Decisions (OpenAI)
Closed APIBase model: undisclosedthe operator's hosted API
Image JevBench v0.3.0 composite score
17.297
Rank #14 of 44 ranked systems.
From the published full-benchmark aggregate. The composite combines intelligence, calibration, speed and cost.
Published axes
- intelligence
- 45.0
- calibration
- 80.7
- speed
- 81.9
- cost
- 32.2
Cost and speed evidence
- Cost per 1,000 decisions
- USD 0.181459
- Cost basis
- OpenRouter usage.cost receipts
- Measured latency · p50 / p95
- 0.405 s / 1.577 s
- Adjusted latency · p50 / p95
- 0.405 s / 1.577 s
- Latency adjustment
- none (hosted API, measured as is)
- Public accuracy
- 62.1%
- Sealed accuracy
- 65.0%
Published 2026-10-06. Scores and ranks can change in a later release. See the method notes.