InternLMInterfaze AIDecision matchup
Intern-Decision-4Bvs.Lev
Which model makes better decisions?
Intern-Decision-4B and Lev each lead in different tests.
Independent testsJev Decision Index
Intern-Decision-4B0 of 1
Lev0 of 1
Popularityout of 100
Intern-Decision-4Bahead40
Lev31
Weights and access
Intern-Decision-4Bopen, local
Levopen, local
SizeParameters
Intern-Decision-4B4 B
Lev4 B
Pick Intern-Decision-4B for
more popular
Pick Lev 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
depends on the subtestLev is clearly ahead in 7 of 37 subtests and slightly in 7, Intern-Decision-4B in 5 clearly and slightly in 4. 14 are level.
SATA-Bench · Decision Index 0.4.1
Intern-Decision-4B30.8
Lev18.2
1,650 tasks, as of October 28, 2026
POP909 · Decision Index 0.4.1
Intern-Decision-4B7.0
Lev5.4
2,000 tasks, as of October 28, 2026
PhishNChips · Decision Index 0.4.1
Intern-Decision-4B61.5
Lev50.6
2,000 tasks, as of October 28, 2026
Show all 37 subtests
| Subtest | Intern-Decision-4B | Lev | Verdict |
|---|---|---|---|
| SATA-Bench · Decision Index 0.4.1 | 30.8 | 18.2 | Intern-Decision-4B ahead |
| POP909 · Decision Index 0.4.1 | 7.0 | 5.4 | Intern-Decision-4B ahead |
| PhishNChips · Decision Index 0.4.1 | 61.5 | 50.6 | Intern-Decision-4B ahead |
| GSM8K · Decision Index 0.4.1 | 25.6 | 29.2 | Lev ahead |
| ChessBench · Decision Index 0.4.1 | 12.6 | 14.3 | Lev ahead |
| When2Call · Decision Index 0.4.1 | 57.8 | 52.3 | Intern-Decision-4B ahead |
| BPoMP · Decision Index 0.4.1 | 81.8 | 87.7 | Lev ahead |
| cfcolor · Decision Index 0.4.1 | 58.5 | 62.2 | Lev ahead |
| MMLU-Pro · Decision Index 0.4.1 | 46.1 | 48.7 | Lev ahead |
| HoVer · Decision Index 0.4.1 | 60.5 | 63.4 | Lev ahead |
| HellaSwag · Decision Index 0.4.1 | 77.6 | 81.2 | Lev ahead |
| BFCL · Decision Index 0.4.1 | 92.7 | 90.2 | Intern-Decision-4B ahead |
| RAGTruth · Decision Index 0.4.1 | 71.9 | 8.3 | Intern-Decision-4B slightly ahead |
| ACOS · Decision Index 0.4.1 | 15.9 | 7.1 | Intern-Decision-4B slightly ahead |
| BANKING77 · Decision Index 0.4.1 | 62.6 | 86.8 | Lev slightly ahead |
| BRIGHT · Decision Index 0.4.1 | 33.1 | 44.0 | Lev slightly ahead |
| CLINC150 · Decision Index 0.4.1 | 72.7 | 90.4 | Lev slightly ahead |
| VAST · Decision Index 0.4.1 | 40.7 | 48.4 | Lev slightly ahead |
| ToolRet · Decision Index 0.4.1 | 52.8 | 62.2 | Lev slightly ahead |
| iSarcasmEval · Decision Index 0.4.1 | 46.4 | 40.0 | Intern-Decision-4B slightly ahead |
| ContractNLI · Decision Index 0.4.1 | 62.0 | 70.4 | Lev slightly ahead |
| ANLI · Decision Index 0.4.1 | 58.4 | 64.5 | Lev slightly ahead |
| FinEntity · Decision Index 0.4.1 | 80.9 | 74.0 | Intern-Decision-4B slightly ahead |
| Home appliances · Decision Index 0.4.1 | 12.5 | 19.3 | level |
| CRUXEval · Decision Index 0.4.1 | 45.1 | 50.3 | level |
| New Yorker · Decision Index 0.4.1 | 58.5 | 54.0 | level |
| API-Bank · Decision Index 0.4.1 | 76.0 | 79.1 | level |
| HLE · Decision Index 0.4.1 | 12.8 | 12.4 | level |
| GPQA Diamond · Decision Index 0.4.1 | 41.3 | 40.3 | level |
| Habermas · Decision Index 0.4.1 | 45.1 | 46.2 | level |
| Humicroedit · Decision Index 0.4.1 | 58.6 | 60.1 | level |
| NLI4CT · Decision Index 0.4.1 | 77.8 | 76.1 | level |
| WinoGrande · Decision Index 0.4.1 | 68.4 | 66.9 | level |
| Amazon ESCI · Decision Index 0.4.1 | 45.3 | 45.9 | level |
| BBH · Decision Index 0.4.1 | 62.1 | 61.3 | level |
| CLadder · Decision Index 0.4.1 | 60.0 | 59.7 | level |
| MuSR · Decision Index 0.4.1 | 53.7 | 53.6 | level |
Source · latest October 28, 2026
All data side by side
| Intern-Decision-4B | Lev | |
|---|---|---|
| Kind | Standalone | Adapter |
| Developer | InternLM | Interfaze AI |
| Status | Open source | Open source |
| Weights | open | open |
| Runs locally | yes | yes |
| Parameters | 4 B | 4 B |
| License | Apache-2.0 with the Qwen notices retained | Apache-2.0 |
| Popularity (out of 100) | 40 | 31 |