PulseAugur
EN
LIVE 08:48:07

VIDRAFT's Darwin-180B-RSI model tops 7 Hugging Face leaderboards

By PulseAugur Editorial · [2 sources] ·

VIDRAFT has released Darwin-180B-RSI, a 180-billion-parameter reasoning model that utilizes a Recursive Self-Improvement (RSI) framework. This model has achieved top rankings on seven Hugging Face leaderboards, including legal reasoning benchmarks like LEXam and LEXam-hard, without being trained on legal data. The RSI approach involves the model solving problems, verifying correctness through automated checks, and then retraining on successful reasoning paths, allowing capabilities to generalize to new domains. The model is available on Hugging Face for public access and verification. AI

IMPACT Sets new SOTA on legal reasoning benchmarks, demonstrating cross-domain generalization via self-improvement.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

VIDRAFT's Darwin-180B-RSI model tops 7 Hugging Face leaderboards

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
46 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. dev.to — LLM tag TIER_1 English(EN) · AI OpenFree ·

    Darwin-180B-RSI: How VIDRAFT's Recursive Self-Improvement Model Topped 7 Hugging Face Leaderboards — Without Legal Training Data

    <h1> Darwin-180B-RSI: How VIDRAFT's Recursive Self-Improvement Model Topped 7 Hugging Face Leaderboards — Without Legal Training Data </h1> <blockquote> <p><strong>TL;DR:</strong> VIDRAFT's <code>Darwin-180B-RSI</code> is a 180-billion-parameter reasoning model trained via a Recu…

  2. dev.to — LLM tag TIER_1 English(EN) · AI OpenFree ·

    Darwin-180B-RSI: VIDRAFT's Recursive Self-Improvement MoE Model Claims Five Leaderboard Tops

    <h1> Darwin-180B-RSI: VIDRAFT's Recursive Self-Improvement MoE Model Claims Five Leaderboard Tops </h1> <blockquote> <p><strong>TL;DR:</strong> VIDRAFT, a Korean Pre-AGI AI startup, has released Darwin-180B-RSI — a 180-billion-parameter mixture-of-experts reasoning model built on…

RELATED ENTITIES

RELATED TOPICS