PT-BR typed decisions Leaderboard
decision-language14 models · Updated October 2026
On the PT-BR typed decisions benchmark, Decider 4B ranks #1 with a score of 64.1. The full ranking, with cost per million tokens, is below.
| # | Model | Score | ECE | p50 latency | Input / 1M |
|---|---|---|---|---|---|
| 1 | Decider 4BMapika | 64.1 | — | — | — |
| 2 | Jet v6.2michaljach | 63.2 | — | — | — |
| 3 | JPT-4Bkirp | 63.2 | — | — | — |
| 4 | Hopper (G) 1.2HopitAI | 63.0 | — | — | — |
| 5 | NeoHorse-Jev-4BTokenRhythm | 62.8 | — | — | — |
| 6 | JevK5 v0.3alibiserikbay | 62.5 | — | — | — |
| 7 | Intern-Decision-4BIntern Large Models | 62.2 | — | — | — |
| 8 | Kev 4B r10Jared Palmer | 62.2 | — | — | $0.04 |
| 9 | levInterfaze | 61.8 | — | — | — |
| 10 | Eikos-4Bcaiovicentino1 | 60.7 | — | — | — |
| 11 | Decision-1.0-Nox-4BvLLM Semantic Router | 59.0 | — | — | — |
| 12 | Kev 0.8B r15Jared Palmer | 50.7 | — | — | — |
| 13 | laya-pt-es-typedtelepatia-ai | 44.6 | — | — | — |
| 14 | LAYAConvai Innovations | 39.2 | — | — | $0.00 |
Frequently asked questions
What is the PT-BR typed decisions benchmark?
PT-BR typed decisions is a decision-language used to evaluate and rank large language models. This page lists 14 models by their PT-BR typed decisions score.
Which model is best on PT-BR typed decisions?
Decider 4B (Mapika) currently leads the PT-BR typed decisions leaderboard with a score of 64.1.
What is the best value model on PT-BR typed decisions?
Pricing data is being matched to these models.
Pricing is indicative — confirm with the provider before production use. Updated October 2026.