Convai InnovationsInternLMDecision matchup
Layavs.Intern-Decision-2B
Which model makes better decisions?
Intern-Decision-2B does better in independent tests, while Laya is much smaller.
Pick Laya for
Pick Intern-Decision-2B 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
Intern-Decision-2B aheadIntern-Decision-2B is clearly ahead in 17 of 37 subtests and slightly in 9, Laya in 2 clearly and slightly in 3. 6 are level.
SATA-Bench · Decision Index 0.4.1
1,650 tasks, as of October 28, 2026
POP909 · Decision Index 0.4.1
2,000 tasks, as of October 28, 2026
When2Call · Decision Index 0.4.1
3,652 tasks, as of October 28, 2026
Show all 37 subtests
| Subtest | Laya | Intern-Decision-2B | Verdict |
|---|---|---|---|
| SATA-Bench · Decision Index 0.4.1 | 0.3 | 11.2 | Intern-Decision-2B ahead |
| POP909 · Decision Index 0.4.1 | 5.1 | 0.9 | Laya ahead |
| When2Call · Decision Index 0.4.1 | 11.9 | 49.1 | Intern-Decision-2B ahead |
| API-Bank · Decision Index 0.4.1 | 11.5 | 28.5 | Intern-Decision-2B ahead |
| MMLU-Pro · Decision Index 0.4.1 | 13.6 | 33.0 | Intern-Decision-2B ahead |
| BFCL · Decision Index 0.4.1 | 38.1 | 71.0 | Intern-Decision-2B ahead |
| HellaSwag · Decision Index 0.4.1 | 33.1 | 60.4 | Intern-Decision-2B ahead |
| New Yorker · Decision Index 0.4.1 | 27.1 | 40.3 | Intern-Decision-2B ahead |
| PhishNChips · Decision Index 0.4.1 | 50.1 | 70.0 | Intern-Decision-2B ahead |
| BBH · Decision Index 0.4.1 | 34.1 | 47.3 | Intern-Decision-2B ahead |
| ChessBench · Decision Index 0.4.1 | 7.7 | 10.6 | Intern-Decision-2B ahead |
| Habermas · Decision Index 0.4.1 | 33.4 | 45.7 | Intern-Decision-2B ahead |
| GSM8K · Decision Index 0.4.1 | 16.9 | 22.0 | Intern-Decision-2B ahead |
| MuSR · Decision Index 0.4.1 | 43.2 | 54.4 | Intern-Decision-2B ahead |
| Humicroedit · Decision Index 0.4.1 | 47.2 | 57.8 | Intern-Decision-2B ahead |
| CRUXEval · Decision Index 0.4.1 | 40.2 | 33.9 | Laya ahead |
| BPoMP · Decision Index 0.4.1 | 51.6 | 58.9 | Intern-Decision-2B ahead |
| WinoGrande · Decision Index 0.4.1 | 50.5 | 57.5 | Intern-Decision-2B ahead |
| cfcolor · Decision Index 0.4.1 | 52.3 | 55.8 | Intern-Decision-2B ahead |
| ToolRet · Decision Index 0.4.1 | 12.8 | 49.0 | Intern-Decision-2B slightly ahead |
| iSarcasmEval · Decision Index 0.4.1 | 14.9 | 28.7 | Intern-Decision-2B slightly ahead |
| RAGTruth · Decision Index 0.4.1 | 48.8 | 29.7 | Laya slightly ahead |
| ContractNLI · Decision Index 0.4.1 | 29.0 | 44.8 | Intern-Decision-2B slightly ahead |
| Amazon ESCI · Decision Index 0.4.1 | 24.4 | 34.6 | Intern-Decision-2B slightly ahead |
| NLI4CT · Decision Index 0.4.1 | 47.7 | 66.3 | Intern-Decision-2B slightly ahead |
| CLINC150 · Decision Index 0.4.1 | 3.2 | 4.3 | Intern-Decision-2B slightly ahead |
| ACOS · Decision Index 0.4.1 | 3.5 | 4.0 | Intern-Decision-2B slightly ahead |
| BANKING77 · Decision Index 0.4.1 | 14.3 | 12.9 | Laya slightly ahead |
| BRIGHT · Decision Index 0.4.1 | 19.9 | 21.4 | Intern-Decision-2B slightly ahead |
| ANLI · Decision Index 0.4.1 | 48.7 | 46.9 | Laya slightly ahead |
| FinEntity · Decision Index 0.4.1 | 61.0 | 63.2 | Intern-Decision-2B slightly ahead |
| Home appliances · Decision Index 0.4.1 | 0.0 | 1.1 | level |
| GPQA Diamond · Decision Index 0.4.1 | 27.6 | 34.2 | level |
| HLE · Decision Index 0.4.1 | 14.0 | 12.8 | level |
| VAST · Decision Index 0.4.1 | 40.5 | 39.3 | level |
| HoVer · Decision Index 0.4.1 | 55.8 | 56.8 | level |
| CLadder · Decision Index 0.4.1 | 52.9 | 53.8 | level |
Source · latest October 28, 2026
Zero-shot IE benchmark
levelZero-shot IE spectrum: mixed-pool classification accuracy
48 tasks, as of October 17, 2026
Source · latest October 17, 2026
All data side by side
| Laya | Intern-Decision-2B | |
|---|---|---|
| Kind | Standalone | Standalone |
| Developer | Convai Innovations | InternLM |
| Status | Open source | Open source |
| Weights | open | open |
| Runs locally | yes | yes |
| Parameters | 0.42 B | 2 B |
| License | Apache-2.0 | Apache-2.0 with the Qwen notices retained |
| Popularity (out of 100) | 0 | 37 |