JevMade Sign in
← Back to experiments

Benchmarks & research

Jev, Llama, and DeepSeek Benchmark

Source screenshot of Jev, Llama, and DeepSeek Benchmark
SOURCE SCREENSHOTFull screenshot ↗

What it does

Ram Vinjamuri compares Jev with fast Llama and DeepSeek models on the same labelled inputs.

Maker-reported (not independently measured by JevMade): Jev: 235 ms median and 82% accuracy · Llama 3.1 8B: 497 ms and 68% accuracy · DeepSeek V4 Flash: about 2 seconds

Primitives
choice
Added

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.