Convai InnovationsMapikaDecision matchup
Laya Typed Decisionsvs.Decider 0.8B
Which model makes better decisions?
Decider 0.8B does better in independent tests, while Laya Typed Decisions is much smaller.
Pick Laya Typed Decisions for
Pick Decider 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”.
Zero-shot IE benchmark
Decider 0.8B aheadDecider 0.8B is clearly ahead in 1 of 4 subtests, Laya Typed Decisions in none. 3 are level.
Zero-shot IE multilingual: medium-resource-language tier accuracy
18 tasks, as of October 17, 2026
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
Show all 4 subtests
| Subtest | Laya Typed Decisions | Decider 0.8B | Verdict |
|---|---|---|---|
| Zero-shot IE multilingual: medium-resource-language tier accuracy | 44.0 % | 100.0 % | Decider 0.8B ahead |
| Zero-shot IE multilingual: rare-language tier accuracy | 33.0 % | 50.0 % | level |
| Zero-shot IE spectrum: mixed-pool classification accuracy | 70.8 | 83.3 | level |
| Zero-shot IE multilingual: popular-language tier accuracy | 100.0 % | 100.0 % | level |
Source · latest October 17, 2026
All data side by side
| Laya Typed Decisions | Decider 0.8B | |
|---|---|---|
| Kind | Standalone | Standalone |
| Developer | Convai Innovations | Mapika |
| Status | Open source | Open source |
| Weights | open | open |
| Runs locally | yes | yes |
| Parameters | 0.42 B | 0.8 B |
| License | Apache-2.0 | Apache-2.0 |
| Popularity (out of 100) | 40 | 39 |