Benchmark Heaven
We track 4 benchmarks that Benchmark Heaven made or helped make.
0 in use 4 with public code 4 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| JevBench Decision models, such as TypeSafe AI's Jev and compatible systems, answer typed decision questions. The board scores accuracy, probability calibration, latency and cost. | Other | Sep 2026 | 98.4% | Not in cards |
| AudioJevBench Models listen to a clip and assign probabilities to answers about speech or sound. The maker checks accuracy and calibration across 988 scored items. | Audio understanding and voice | Sep 2026 | | Not in cards |
| ImageJevBench v0.1.5 Models answer decisions about images and assign probabilities to the answers. The maker ranks capability using accuracy and calibration within cost and latency limits. | General visual questions | Oct 2026 | 16.1 | Not in cards |
| ImageJevBench v0.3.0 Models make decisions about images and report probabilities. This version draws 300 public and 1,200 sealed items from a new pool. | General visual questions | Oct 2026 | 17.3 | Not in cards |