Skip to main content

Jared PalmerDecision matchup

Kev 0.8Bvs.Kev 0.5B

Which model makes better decisions?

Kev 0.8B does better in independent tests.

Independent tests
Kev 0.8Bahead1 of 1
Kev 0.5B0 of 1
JevAny external decision-suite evaluation score table
Popularity
Kev 0.8Bahead45
Kev 0.5B31
out of 100
Weights and access
Kev 0.8Bopen, local
Kev 0.5Bopen, local
Released
Kev 0.8BSeptember 20, 2026
Kev 0.5Bn/a

Pick Kev 0.8B for

JevAny external decision-suite evaluation score tablemore popular

Pick Kev 0.5B for

No clear edge

Shared tests

Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.

JevAny external decision-suite evaluation score table

Kev 0.8B ahead

MMLU-Pro, ekzhang external test panel (1,000 questions)

Kev 0.8B23.3
Kev 0.5B16.2

1,000 tasks, as of October 17, 2026

Source · latest October 17, 2026

All data side by side

Kev 0.8BKev 0.5B
KindAdapterAdapter
DeveloperJared PalmerJared Palmer
StatusOpen sourceLegacy
ReleasedSeptember 20, 2026n/a
Weightsopenopen
Runs locallyyesyes
LicenseApache-2.0 for the adapter and headApache-2.0 for the adapter and head
Popularity (out of 100)4531

More comparisons with Kev 0.8B and Kev 0.5B

Decider 2Bvs.Kev 0.8BKev 0.8Bvs.Clef-FlashKev 0.8Bvs.GLiNER2.5-DecideDecider 4Bvs.Kev 0.8BKev 0.8Bvs.Intern-Decision-4BLaya Typed Decisionsvs.Kev 0.8BKev 0.8Bvs.Kev 9BDecider 0.8Bvs.Kev 0.8BKev 0.8Bvs.Julia 1

All decision models compared