Jared PalmerInternLMDecision matchup
Kev 0.8Bvs.Intern-Decision-0.8B
Which model makes better decisions?
Kev 0.8B does better in independent tests.
Pick Kev 0.8B for
Pick Intern-Decision-0.8B for
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
depends on the subtestKev 0.8B is clearly ahead in 4 of 37 subtests and slightly in 8, Intern-Decision-0.8B in 5 clearly and slightly in 3. 17 are level.
SATA-Bench · Decision Index 0.4.1
1,650 tasks, as of October 28, 2026
API-Bank · Decision Index 0.4.1
508 tasks, as of October 28, 2026
Habermas · Decision Index 0.4.1
1,676 tasks, as of October 28, 2026
Show all 37 subtests
| Subtest | Kev 0.8B | Intern-Decision-0.8B | Verdict |
|---|---|---|---|
| SATA-Bench · Decision Index 0.4.1 | 9.0 | 3.4 | Kev 0.8B ahead |
| API-Bank · Decision Index 0.4.1 | 43.7 | 21.1 | Kev 0.8B ahead |
| Habermas · Decision Index 0.4.1 | 33.4 | 44.6 | Intern-Decision-0.8B ahead |
| MMLU-Pro · Decision Index 0.4.1 | 22.3 | 26.5 | Intern-Decision-0.8B ahead |
| PhishNChips · Decision Index 0.4.1 | 51.7 | 45.9 | Kev 0.8B ahead |
| BFCL · Decision Index 0.4.1 | 70.5 | 64.5 | Kev 0.8B ahead |
| When2Call · Decision Index 0.4.1 | 43.2 | 46.1 | Intern-Decision-0.8B ahead |
| BPoMP · Decision Index 0.4.1 | 47.7 | 50.4 | Intern-Decision-0.8B ahead |
| Humicroedit · Decision Index 0.4.1 | 50.9 | 53.7 | Intern-Decision-0.8B ahead |
| BANKING77 · Decision Index 0.4.1 | 77.6 | 11.9 | Kev 0.8B slightly ahead |
| CLINC150 · Decision Index 0.4.1 | 15.0 | 4.9 | Kev 0.8B slightly ahead |
| ACOS · Decision Index 0.4.1 | 9.9 | 4.6 | Kev 0.8B slightly ahead |
| VAST · Decision Index 0.4.1 | 40.6 | 28.0 | Kev 0.8B slightly ahead |
| BRIGHT · Decision Index 0.4.1 | 31.8 | 22.4 | Kev 0.8B slightly ahead |
| iSarcasmEval · Decision Index 0.4.1 | 19.9 | 26.3 | Intern-Decision-0.8B slightly ahead |
| FinEntity · Decision Index 0.4.1 | 71.4 | 57.1 | Kev 0.8B slightly ahead |
| RAGTruth · Decision Index 0.4.1 | 46.2 | 53.3 | Intern-Decision-0.8B slightly ahead |
| ContractNLI · Decision Index 0.4.1 | 40.9 | 35.4 | Kev 0.8B slightly ahead |
| ToolRet · Decision Index 0.4.1 | 51.7 | 47.4 | Kev 0.8B slightly ahead |
| Amazon ESCI · Decision Index 0.4.1 | 22.9 | 24.4 | Intern-Decision-0.8B slightly ahead |
| GPQA Diamond · Decision Index 0.4.1 | 33.2 | 28.1 | level |
| CRUXEval · Decision Index 0.4.1 | 37.7 | 32.8 | level |
| ChessBench · Decision Index 0.4.1 | 7.9 | 8.8 | level |
| POP909 · Decision Index 0.4.1 | 1.5 | 1.6 | level |
| MuSR · Decision Index 0.4.1 | 48.9 | 51.3 | level |
| NLI4CT · Decision Index 0.4.1 | 55.9 | 57.7 | level |
| BBH · Decision Index 0.4.1 | 41.4 | 42.7 | level |
| New Yorker · Decision Index 0.4.1 | 27.8 | 27.1 | level |
| HoVer · Decision Index 0.4.1 | 51.0 | 52.3 | level |
| cfcolor · Decision Index 0.4.1 | 55.4 | 56.7 | level |
| GSM8K · Decision Index 0.4.1 | 19.0 | 18.6 | level |
| HellaSwag · Decision Index 0.4.1 | 42.9 | 43.6 | level |
| ANLI · Decision Index 0.4.1 | 33.6 | 34.1 | level |
| HLE · Decision Index 0.4.1 | 13.8 | 13.6 | level |
| WinoGrande · Decision Index 0.4.1 | 52.8 | 53.1 | level |
| CLadder · Decision Index 0.4.1 | 50.5 | 50.5 | level |
| Home appliances · Decision Index 0.4.1 | 0.0 | 0.0 | level |
Source · latest October 28, 2026
Zero-shot IE benchmark
levelKev 0.8B is clearly ahead in 0 of 4 subtests, Intern-Decision-0.8B in none. 4 are level.
Zero-shot IE multilingual: rare-language tier accuracy
18 tasks, as of October 17, 2026
Zero-shot IE spectrum: mixed-pool classification accuracy
48 tasks, as of October 17, 2026
Zero-shot IE multilingual: medium-resource-language tier accuracy
18 tasks, as of October 17, 2026
Show all 4 subtests
| Subtest | Kev 0.8B | Intern-Decision-0.8B | Verdict |
|---|---|---|---|
| Zero-shot IE multilingual: rare-language tier accuracy | 50.0 % | 78.0 % | level |
| Zero-shot IE spectrum: mixed-pool classification accuracy | 72.9 | 77.1 | level |
| Zero-shot IE multilingual: medium-resource-language tier accuracy | 89.0 % | 94.0 % | level |
| Zero-shot IE multilingual: popular-language tier accuracy | 94.0 % | 94.0 % | level |
Source · latest October 17, 2026
Duan et al., General Decision Models: Benchmarking and Insights Beyond Jev
Kev 0.8B aheadJEVal aida-testc accuracy
200 tasks, as of October 22, 2026
Source · latest October 22, 2026
All data side by side
| Kev 0.8B | Intern-Decision-0.8B | |
|---|---|---|
| Kind | Adapter | Standalone |
| Developer | Jared Palmer | InternLM |
| Status | Open source | Open source |
| Released | September 20, 2026 | n/a |
| Weights | open | open |
| Runs locally | yes | yes |
| Parameters | n/a | 0.8 B |
| License | Apache-2.0 for the adapter and head | Apache-2.0 with the Qwen notices retained |
| Popularity (out of 100) | 45 | 38 |