Live site · by florianstandhar
JevBench
A reproducible benchmark for typed decision models.
florianstandhar’s JevBench is a reproducible benchmark for typed decision models, published on Benchmark Heaven.
Open the sourceMore like this
Wayne Sutton
@waynesutton
Ask Jev anything. Give it a try at askjev.ai It won't answer. It will judge. Let's see if we can get to 1 million questions. @typesafeai 🤝 @convex work great together. @hmartenjoyer @CompleteSkeptic @justKDeng @mikeysee
Live siteBenchmarks and evals
askjev.ai
Benchmark Heaven
@benchmarkheaven
Hopper (#3) beats Jev 1.13.0 on three of four columns: Calibration 79.1 vs 76.3, Speed 86.8 vs 83.3, Cost 58.7 vs 52.0. Jev keeps #1 on the fourth: Intelligence 53.1 vs 48.0, hard tier 74.1% vs 65.0%. Under 50, the gate applies. Score 63.29 vs 59.43. benchmarkheaven.com/jev-models/v1.…
Live siteBenchmarks and evals
Jev 1.13.0 against Hopper on Benchmark Heaven
- Intelligence
- 53.1 vs 48.0
- Calibration
- 76.3 vs 79.1
- Hard tier
- 74.1% vs 65.0%
- Score
- 63.29 vs 59.43
apolinario (poli)
@multimodalart
the jev Decision Index v0.3 is here 🎯 featuring a way stronger set of benchmarks, now with a strong private half 🔒 so the ranking tracks skills beyond benchmarks and, as promised, vision 👁️ huggingface.co/spaces/multimo…
Live siteBenchmarks and evals
Jev Decision Index v0.3
