apolinario

Model (Safetensors, Apache 2.0): huggingface.co Full JEV Index 0.3 Public Split Runs (152,388 rows): huggingface.co K=8 Hard-Negative Routing Dataset (15,884 episodes): huggingface.co Official decision-index Engine PR #350: decision-index#350 cc @multimodalart @mrm8488

Créditos: El análisis está publicado en github por el usuario apolinario (@multimodalart), incluyendo el código fuente y las instrucciones para descargar los logs oficiales y correr el analisis localmente apolinario/urnas-tardias

Oi Marçal, os dados estão abertos no site do TSE desde o fim da totalização dos votos. Eu os processei e abri o código no GitHub para que qualquer cidadão possa reproduzir a análise apolinario/urnas-tardias Fonte: insta: Apolinariosteps

É ainda menor, porque esses dados ainda consideram quem tava na fila às 17h. Se colocar o corte em 17h15, não são nem 6 mil votos: (Análise do Apolinário: apolinario/urnas-tardias)

Don't be fooled about Brasil. Both parties asked for an extension. Only 1.48% of voting stations were actually extended. They only received 0.004% of all votes. These votes (which also include votes for Bolsonaro) represent only 0.11% of Lula's advantage. Code is here: apolinario/urnas-tardias

Análise independente dos dados do TSE (em repositório público), mostra que a extensão no horário das eleições não teve impacto algum nos resultados. preview.redd.it apolinario/urnas-tardias

ESPALHEM! #LulaReeleito #LulaPelaDemocracia #LulaOMaiorDeTodos Fonte: apolinario/urnas-tardias t.co

analisei os dados oficiais das urnas do TSE e o voto tardio foi completamente irrisório no resultado eleitoral abri o código pra qualquer um que queira reproduzir a análise apolinario/urnas-tardias t.co

@multimodalart Before you trust this leaderboard: we submitted our model on Sept 27 and it is still not listed. The maintainer wrote that it "fell through the cracks" and that he was running it, then deleted the comment. 37 models were added after that. Still no answer. decision-index#85

Aplomb 1: open-weights 5.3B decision model, 1M context, text/image/video/audio in one request, #1 among 4B models on the Decision Index We released Aplomb 1 today, a 5.3B decision model with open weights. It reads up to 1M tokens of text, JSON, images, video and audio in a single request, and on our API it makes a decision on a 1M-token document in about 3 seconds, at $0.02 per 1M input tokens with free output and ZDR by default. On Decision Index 0.2.1 it scores 44.86 on our run of the official kit, #1 among 4B models on the published board, and it has the top score among models up to 5.3B on 8 of the 38 benchmarks, including MMLU-Pro, GPQA Diamond and BBH. We've submitted it to the board, and the full run is public. It also scores 77.5% on JevBench Hard and averages 75% zero-shot intent accuracy across 51 languages on MASSIVE. As far as we know, it's the only decision model that returns probabilities for tool arguments, reads 1M tokens, or takes text, images, video and audio together. Tool selection gives a probability for every tool and for each enum and boolean argument in one request: on "Order B-44120 arrived with a cracked screen. I want my money back." with three tools, it picks issue_refund at 0.969, reason "damaged" at 0.993 and full_refund true at 0.761, so an agent can act on confident calls and hand the rest to a larger model. Any question can also return the probability that the input doesn't contain the answer. The 1M-token speed comes from a long-context mode in our own inference runtime: about 3 seconds instead of about 111 for a full read, and it answered all 525 decisions in our long-context tests correctly. It's currently only available on our API, so the open weights read every token. On the API, a short question takes about 15 ms of model time (around 200ms e2e latency), and the OpenAI, Anthropic and Gemini formats work alongside our Decisions API. Aplomb 1 is built on Qwen3.5-4B with the audio encoder from Qwen3-Omni-30B-A3B-Instruct, both Apache-2.0. We extended the window from 262K to 1M tokens, added our own decision head and trained the model for decisions. Thanks to the Qwen team. Disclosure: the training data included the public train splits of WinoGrande and ContractNLI, two of the 38 index benchmarks. The weights run in bf16 on about 12 GB of GPU memory with the reference script, under the EmpirioLabs Model License, which is free for research, evaluation, personal use and internal use at companies under $1M in annual revenue. Weights: huggingface.co Blog with the full tables: empiriolabs.ai Docs: docs.empiriolabs.ai Playground: platform.empiriolabs.ai