InternLMInterfaze AIDecision matchup
Intern-Decision-2Bvs.Lev
Which model makes better decisions?
Lev does better in independent tests, while Intern-Decision-2B is much smaller.
Pick Intern-Decision-2B for
Pick Lev 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
Lev aheadLev is clearly ahead in 18 of 37 subtests and slightly in 12, Intern-Decision-2B in 1 clearly and slightly in 1. 5 are level.
Home appliances · Decision Index 0.4.1
88 tasks, as of October 28, 2026
POP909 · Decision Index 0.4.1
2,000 tasks, as of October 28, 2026
API-Bank · Decision Index 0.4.1
508 tasks, as of October 28, 2026
Show all 37 subtests
| Subtest | Intern-Decision-2B | Lev | Verdict |
|---|---|---|---|
| Home appliances · Decision Index 0.4.1 | 1.1 | 19.3 | Lev ahead |
| POP909 · Decision Index 0.4.1 | 0.9 | 5.4 | Lev ahead |
| API-Bank · Decision Index 0.4.1 | 28.5 | 79.1 | Lev ahead |
| SATA-Bench · Decision Index 0.4.1 | 11.2 | 18.2 | Lev ahead |
| BPoMP · Decision Index 0.4.1 | 58.9 | 87.7 | Lev ahead |
| CRUXEval · Decision Index 0.4.1 | 33.9 | 50.3 | Lev ahead |
| MMLU-Pro · Decision Index 0.4.1 | 33.0 | 48.7 | Lev ahead |
| PhishNChips · Decision Index 0.4.1 | 70.0 | 50.6 | Intern-Decision-2B ahead |
| ChessBench · Decision Index 0.4.1 | 10.6 | 14.3 | Lev ahead |
| HellaSwag · Decision Index 0.4.1 | 60.4 | 81.2 | Lev ahead |
| New Yorker · Decision Index 0.4.1 | 40.3 | 54.0 | Lev ahead |
| GSM8K · Decision Index 0.4.1 | 22.0 | 29.2 | Lev ahead |
| BBH · Decision Index 0.4.1 | 47.3 | 61.3 | Lev ahead |
| BFCL · Decision Index 0.4.1 | 71.0 | 90.2 | Lev ahead |
| WinoGrande · Decision Index 0.4.1 | 57.5 | 66.9 | Lev ahead |
| HoVer · Decision Index 0.4.1 | 56.8 | 63.4 | Lev ahead |
| cfcolor · Decision Index 0.4.1 | 55.8 | 62.2 | Lev ahead |
| CLadder · Decision Index 0.4.1 | 53.8 | 59.7 | Lev ahead |
| When2Call · Decision Index 0.4.1 | 49.1 | 52.3 | Lev ahead |
| CLINC150 · Decision Index 0.4.1 | 4.3 | 90.4 | Lev slightly ahead |
| BANKING77 · Decision Index 0.4.1 | 12.9 | 86.8 | Lev slightly ahead |
| RAGTruth · Decision Index 0.4.1 | 29.7 | 8.3 | Intern-Decision-2B slightly ahead |
| BRIGHT · Decision Index 0.4.1 | 21.4 | 44.0 | Lev slightly ahead |
| ACOS · Decision Index 0.4.1 | 4.0 | 7.1 | Lev slightly ahead |
| ContractNLI · Decision Index 0.4.1 | 44.8 | 70.4 | Lev slightly ahead |
| iSarcasmEval · Decision Index 0.4.1 | 28.7 | 40.0 | Lev slightly ahead |
| ANLI · Decision Index 0.4.1 | 46.9 | 64.5 | Lev slightly ahead |
| Amazon ESCI · Decision Index 0.4.1 | 34.6 | 45.9 | Lev slightly ahead |
| ToolRet · Decision Index 0.4.1 | 49.0 | 62.2 | Lev slightly ahead |
| VAST · Decision Index 0.4.1 | 39.3 | 48.4 | Lev slightly ahead |
| FinEntity · Decision Index 0.4.1 | 63.2 | 74.0 | Lev slightly ahead |
| NLI4CT · Decision Index 0.4.1 | 66.3 | 76.1 | Lev slightly ahead |
| GPQA Diamond · Decision Index 0.4.1 | 34.2 | 40.3 | level |
| Humicroedit · Decision Index 0.4.1 | 57.8 | 60.1 | level |
| HLE · Decision Index 0.4.1 | 12.8 | 12.4 | level |
| MuSR · Decision Index 0.4.1 | 54.4 | 53.6 | level |
| Habermas · Decision Index 0.4.1 | 45.7 | 46.2 | level |
Source · latest October 28, 2026
All data side by side
| Intern-Decision-2B | Lev | |
|---|---|---|
| Kind | Standalone | Adapter |
| Developer | InternLM | Interfaze AI |
| Status | Open source | Open source |
| Weights | open | open |
| Runs locally | yes | yes |
| Parameters | 2 B | 4 B |
| License | Apache-2.0 with the Qwen notices retained | Apache-2.0 |
| Popularity (out of 100) | 37 | 31 |