Skip to main content

Jared PalmerCloudflareDecision matchup

Kev 9Bvs.Clef

Which model makes better decisions?

Clef is slightly ahead in independent tests, but the lead is not certain.

Independent tests
Kev 9B0 of 1
Clef0 of 1
AIMultiple decision-models evaluation
Popularity
Kev 9B40
Clefahead51
out of 100
Weights and access
Kev 9Bopen, local
Clefopen, local
Size
Kev 9Bn/a
Clef27 B
Parameters

Pick Kev 9B for

No clear edge

Pick Clef for

leaning AIMultiple decision-models evaluationmore popular

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”.

AIMultiple decision-models evaluation

Clef slightly ahead

Clef is clearly ahead in 0 of 4 subtests and slightly in 4, Kev 9B in none.

AIMultiple decision-task benchmark: Task done check

Kev 9B90.20
Clef99.50

as of October 18, 2026

AIMultiple decision-task benchmark: Recall danger level

Kev 9B56.70
Clef59.20

500 tasks, as of October 18, 2026

AIMultiple decision-task benchmark: Research paper topic

Kev 9B67.60
Clef70.20

500 tasks, as of October 18, 2026

Show all 4 subtests
SubtestKev 9BClefVerdict
AIMultiple decision-task benchmark: Task done check90.2099.50Clef slightly ahead
AIMultiple decision-task benchmark: Recall danger level56.7059.20Clef slightly ahead
AIMultiple decision-task benchmark: Research paper topic67.6070.20Clef slightly ahead
AIMultiple decision-task benchmark: Security flaw severity41.4042.70Clef slightly ahead

Source · latest October 18, 2026

All data side by side

Kev 9BClef
KindAdapterStandalone
DeveloperJared PalmerCloudflare
StatusOpen sourceActive
ReleasedSeptember 20, 2026October 1, 2026
Weightsopenopen
Runs locallyyesyes
Parametersn/a27 B
LicenseApache-2.0 for the adapter and headApache-2.0
Pricen/a$0.240 per 1M input tokens (21,818 neurons per 1M)
Popularity (out of 100)4051