Jared PalmerContrastive-LMDecision matchup
Kev 0.8Bvs.CLM-v0.1-8B
Which model makes better decisions?
Kev 0.8B does better in independent tests.
Independent testsJev Decision Index
Kev 0.8Bahead1 of 1
CLM-v0.1-8B0 of 1
Popularityout of 100
Kev 0.8Bahead45
CLM-v0.1-8B37
Weights and access
Kev 0.8Bopen, local
CLM-v0.1-8Bopen, local
SizeParameters
Kev 0.8Bn/a
CLM-v0.1-8B8 B
Pick Kev 0.8B for
Jev Decision Indexmore popular
Pick CLM-v0.1-8B 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”.
Jev Decision Index
Kev 0.8B aheadKev 0.8B is clearly ahead in 12 of 37 subtests and slightly in 10, CLM-v0.1-8B in 4 clearly and slightly in 2. 9 are level.
POP909 · Decision Index 0.4.1
Kev 0.8B1.5
CLM-v0.1-8B0.0
2,000 tasks, as of October 28, 2026
API-Bank · Decision Index 0.4.1
Kev 0.8B43.7
CLM-v0.1-8B6.1
508 tasks, as of October 28, 2026
BFCL · Decision Index 0.4.1
Kev 0.8B70.5
CLM-v0.1-8B38.9
1,694 tasks, as of October 28, 2026
Show all 37 subtests
| Subtest | Kev 0.8B | CLM-v0.1-8B | Verdict |
|---|---|---|---|
| POP909 · Decision Index 0.4.1 | 1.5 | 0.0 | Kev 0.8B ahead |
| API-Bank · Decision Index 0.4.1 | 43.7 | 6.1 | Kev 0.8B ahead |
| BFCL · Decision Index 0.4.1 | 70.5 | 38.9 | Kev 0.8B ahead |
| GPQA Diamond · Decision Index 0.4.1 | 33.2 | 20.4 | Kev 0.8B ahead |
| SATA-Bench · Decision Index 0.4.1 | 9.0 | 5.6 | Kev 0.8B ahead |
| MMLU-Pro · Decision Index 0.4.1 | 22.3 | 14.7 | Kev 0.8B ahead |
| BPoMP · Decision Index 0.4.1 | 47.7 | 32.9 | Kev 0.8B ahead |
| MuSR · Decision Index 0.4.1 | 48.9 | 34.6 | Kev 0.8B ahead |
| BBH · Decision Index 0.4.1 | 41.4 | 30.8 | Kev 0.8B ahead |
| PhishNChips · Decision Index 0.4.1 | 51.7 | 65.1 | CLM-v0.1-8B ahead |
| When2Call · Decision Index 0.4.1 | 43.2 | 38.7 | Kev 0.8B ahead |
| Habermas · Decision Index 0.4.1 | 33.4 | 37.1 | CLM-v0.1-8B ahead |
| Humicroedit · Decision Index 0.4.1 | 50.9 | 55.6 | CLM-v0.1-8B ahead |
| cfcolor · Decision Index 0.4.1 | 55.4 | 50.8 | Kev 0.8B ahead |
| CLadder · Decision Index 0.4.1 | 50.5 | 53.9 | CLM-v0.1-8B ahead |
| HellaSwag · Decision Index 0.4.1 | 42.9 | 40.4 | Kev 0.8B ahead |
| BANKING77 · Decision Index 0.4.1 | 77.6 | 6.5 | Kev 0.8B slightly ahead |
| Amazon ESCI · Decision Index 0.4.1 | 22.9 | 5.0 | Kev 0.8B slightly ahead |
| ACOS · Decision Index 0.4.1 | 9.9 | 3.1 | Kev 0.8B slightly ahead |
| FinEntity · Decision Index 0.4.1 | 71.4 | 33.4 | Kev 0.8B slightly ahead |
| ContractNLI · Decision Index 0.4.1 | 40.9 | 20.1 | Kev 0.8B slightly ahead |
| VAST · Decision Index 0.4.1 | 40.6 | 22.7 | Kev 0.8B slightly ahead |
| CLINC150 · Decision Index 0.4.1 | 15.0 | 8.9 | Kev 0.8B slightly ahead |
| iSarcasmEval · Decision Index 0.4.1 | 19.9 | 31.2 | CLM-v0.1-8B slightly ahead |
| ToolRet · Decision Index 0.4.1 | 51.7 | 40.3 | Kev 0.8B slightly ahead |
| RAGTruth · Decision Index 0.4.1 | 46.2 | 51.8 | CLM-v0.1-8B slightly ahead |
| BRIGHT · Decision Index 0.4.1 | 31.8 | 29.2 | Kev 0.8B slightly ahead |
| ANLI · Decision Index 0.4.1 | 33.6 | 31.6 | Kev 0.8B slightly ahead |
| HLE · Decision Index 0.4.1 | 13.8 | 15.8 | level |
| CRUXEval · Decision Index 0.4.1 | 37.7 | 42.8 | level |
| New Yorker · Decision Index 0.4.1 | 27.8 | 25.4 | level |
| GSM8K · Decision Index 0.4.1 | 19.0 | 17.5 | level |
| WinoGrande · Decision Index 0.4.1 | 52.8 | 50.8 | level |
| ChessBench · Decision Index 0.4.1 | 7.9 | 8.2 | level |
| HoVer · Decision Index 0.4.1 | 51.0 | 52.0 | level |
| NLI4CT · Decision Index 0.4.1 | 55.9 | 56.5 | level |
| Home appliances · Decision Index 0.4.1 | 0.0 | 0.0 | level |
Source · latest October 28, 2026
All data side by side
| Kev 0.8B | CLM-v0.1-8B | |
|---|---|---|
| Kind | Adapter | Standalone |
| Developer | Jared Palmer | Contrastive-LM |
| Status | Open source | Open weights |
| Released | September 20, 2026 | n/a |
| Weights | open | open |
| Runs locally | yes | yes |
| Parameters | n/a | 8 B |
| License | Apache-2.0 for the adapter and head | Apache-2.0 |
| Popularity (out of 100) | 45 | 37 |