Jared PalmerCloudflareDecision matchup
Kev 4Bvs.Clef-Flash
Which model makes better decisions?
Clef-Flash does better in independent tests.
Independent testsJev Decision Index
Kev 4B0 of 1
Clef-Flashahead1 of 1
Popularityout of 100
Kev 4B23
Clef-Flashahead51
Weights and access
Kev 4Bopen, local
Clef-Flashopen, local
SizeParameters
Kev 4Bn/a
Clef-Flash9 B
Pick Kev 4B for
No clear edge
Pick Clef-Flash for
Jev Decision Indexmore 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”.
Jev Decision Index
Clef-Flash aheadClef-Flash is clearly ahead in 19 of 37 subtests and slightly in 8, Kev 4B in 0 clearly and slightly in 4. 6 are level.
Home appliances · Decision Index 0.4.1
Kev 4B14.8
Clef-Flash97.7
88 tasks, as of October 28, 2026
ChessBench · Decision Index 0.4.1
Kev 4B8.9
Clef-Flash23.1
5,000 tasks, as of October 28, 2026
CRUXEval · Decision Index 0.4.1
Kev 4B48.1
Clef-Flash86.5
570 tasks, as of October 28, 2026
Show all 37 subtests
| Subtest | Kev 4B | Clef-Flash | Verdict |
|---|---|---|---|
| Home appliances · Decision Index 0.4.1 | 14.8 | 97.7 | Clef-Flash ahead |
| ChessBench · Decision Index 0.4.1 | 8.9 | 23.1 | Clef-Flash ahead |
| CRUXEval · Decision Index 0.4.1 | 48.1 | 86.5 | Clef-Flash ahead |
| API-Bank · Decision Index 0.4.1 | 53.3 | 93.1 | Clef-Flash ahead |
| Habermas · Decision Index 0.4.1 | 42.0 | 71.8 | Clef-Flash ahead |
| CLadder · Decision Index 0.4.1 | 63.1 | 97.7 | Clef-Flash ahead |
| MuSR · Decision Index 0.4.1 | 56.3 | 86.2 | Clef-Flash ahead |
| BPoMP · Decision Index 0.4.1 | 65.1 | 95.4 | Clef-Flash ahead |
| WinoGrande · Decision Index 0.4.1 | 70.2 | 97.6 | Clef-Flash ahead |
| Humicroedit · Decision Index 0.4.1 | 54.4 | 75.1 | Clef-Flash ahead |
| GPQA Diamond · Decision Index 0.4.1 | 37.8 | 51.5 | Clef-Flash ahead |
| PhishNChips · Decision Index 0.4.1 | 55.3 | 75.1 | Clef-Flash ahead |
| MMLU-Pro · Decision Index 0.4.1 | 50.7 | 65.2 | Clef-Flash ahead |
| SATA-Bench · Decision Index 0.4.1 | 28.8 | 36.6 | Clef-Flash ahead |
| New Yorker · Decision Index 0.4.1 | 52.3 | 66.3 | Clef-Flash ahead |
| HellaSwag · Decision Index 0.4.1 | 78.9 | 98.6 | Clef-Flash ahead |
| cfcolor · Decision Index 0.4.1 | 57.9 | 65.9 | Clef-Flash ahead |
| BBH · Decision Index 0.4.1 | 62.5 | 68.9 | Clef-Flash ahead |
| BFCL · Decision Index 0.4.1 | 93.1 | 98.8 | Clef-Flash ahead |
| ACOS · Decision Index 0.4.1 | 9.8 | 26.0 | Clef-Flash slightly ahead |
| iSarcasmEval · Decision Index 0.4.1 | 46.8 | 19.7 | Kev 4B slightly ahead |
| RAGTruth · Decision Index 0.4.1 | 67.5 | 35.6 | Kev 4B slightly ahead |
| Amazon ESCI · Decision Index 0.4.1 | 39.7 | 57.4 | Clef-Flash slightly ahead |
| ContractNLI · Decision Index 0.4.1 | 64.4 | 84.5 | Clef-Flash slightly ahead |
| ANLI · Decision Index 0.4.1 | 48.1 | 59.1 | Clef-Flash slightly ahead |
| CLINC150 · Decision Index 0.4.1 | 75.0 | 66.9 | Kev 4B slightly ahead |
| FinEntity · Decision Index 0.4.1 | 87.1 | 97.1 | Clef-Flash slightly ahead |
| BANKING77 · Decision Index 0.4.1 | 82.9 | 90.8 | Clef-Flash slightly ahead |
| ToolRet · Decision Index 0.4.1 | 61.0 | 66.2 | Clef-Flash slightly ahead |
| VAST · Decision Index 0.4.1 | 52.4 | 49.6 | Kev 4B slightly ahead |
| NLI4CT · Decision Index 0.4.1 | 74.6 | 78.6 | Clef-Flash slightly ahead |
| POP909 · Decision Index 0.4.1 | 1.2 | 1.6 | level |
| HLE · Decision Index 0.4.1 | 10.2 | 11.8 | level |
| HoVer · Decision Index 0.4.1 | 59.7 | 61.2 | level |
| When2Call · Decision Index 0.4.1 | 66.7 | 65.3 | level |
| BRIGHT · Decision Index 0.4.1 | 39.0 | 38.3 | level |
| GSM8K · Decision Index 0.4.1 | 46.5 | 46.7 | level |
Source · latest October 28, 2026
All data side by side
| Kev 4B | Clef-Flash | |
|---|---|---|
| Kind | Adapter | Standalone |
| Developer | Jared Palmer | Cloudflare |
| Status | Open source | Active |
| Released | September 20, 2026 | October 1, 2026 |
| Weights | open | open |
| Runs locally | yes | yes |
| Parameters | n/a | 9 B |
| License | Apache-2.0 for the adapter and head | Apache-2.0 |
| Price | n/a | $0.090 per 1M input tokens (8,182 neurons per 1M) |
| Popularity (out of 100) | 23 | 51 |