Probability-Only Jev Model Matches GPT-5.6 in 42 of 49 Tasks
TypeSafe's Jev, a model that outputs only probabilities for typed questions without generating text, matched or beat GPT-5.6-luna on 42 of 49 benchmark tasks. Critics note the comparison is unfair since Jev is not an LLM, and further tests show it wins on accuracy but loses on speed.
2026-09-19 ~ 2026-09-19 · 3 related posts
- Episode 1: TypeSafe exits stealth with decision model Jev and RLCD training method(2026-09-16, 86 posts)
- Episode 2: TypeSafe AI launches Jev, a dedicated evaluation model showing major speed and cost gains in tests(2026-09-16, 8 posts)
- Episode 3: Vercel fx to adopt Jev safety reviewer, up to 18x faster(2026-09-17, 3 posts)
- Episode 4: OpenJev Open-Source Clone Runs Jev-Style API on One RTX 3090(2026-09-17, 3 posts)
- Episode 5: TypeSafe AI Launches Jev, a Decision-Only Model That Outputs No Text(2026-09-17, 73 posts)
- Episode 6: Jev Ecosystem Grows: Six GitHub Projects Span Browser Agents to Auto-Trading(2026-09-18, 2 posts)
- Episode 7: Jev: Decision-Oriented AI Sparks New Business Opportunities(2026-09-18, 2 posts)
- Episode 8: TypeSafe Jev's LLM Probability Trick Is Easy for Giants to Copy(2026-09-18, 2 posts)
- Episode 9: TypeSafe AI Launches Jev, Claiming 200x Faster and 400x Cheaper Classification(2026-09-19, 6 posts)
- Episode 10: Probability-Only Jev Model Matches GPT-5.6 in 42 of 49 Tasks(2026-09-19, 3 posts)
- Jev Wins on Accuracy but Loses at the Speed It's Named For, When Benchmarked Against Open-Weight Encoders — alexisgallagher · 2026-09-19
- Probability-Only Model Jev Beats or Matches GPT-5.6-luna on 42 of 49 Tasks at 4x Speed, 1/4 Cost — LowNefariousness9966 · 2026-09-19
1 near-duplicate retellings: LowNefariousness9966