FINAL_Bench

Team

company

https://www.vidraft.net

Activity Feed

AI & ML interests

Contact: arxivgpt@gmail.com

Recent Activity

SeaWolf-AI updated a Space about 6 hours ago

FINAL-Bench/finchal

SeaWolf-AI updated a Space about 8 hours ago

FINAL-Bench/leadboard

SeaWolf-AI published an article 1 day ago

Writing Down the Line Between Luck and Skill

View all activity

Papers

Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning

View all Papers

Articles

POCKET: a 35-billion-parameter model that runs on your iPhone — and on your PC with no GPU

Jul 23

• 12

Aether-7B-5Attn: A 100% Open-Source Sovereign Foundation Model — and a Controlled Experiment in Heterogeneous Attention

Jul 19

• 21

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

Jul 12

• 17

Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier

Jul 5

• 15

Adding a GPU Without Building One

Jul 3

• 17

Chitos: From Detection to Proof — An Autonomous Security AI That Actually Exploits

Jun 29

• 19

FINAL-Bench Quantum: An Open, Neutral Benchmark for Quantum-Computing Methods

Jun 14

• 17

Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step

May 15

• 18

Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion

Apr 15

• 13

"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"

Apr 13

• 16

Darwin V6: Diagnostic-Guided Evolutionary Model Merging

Apr 8

• 12

"The Child That Surpassed Both Parents Through MRI-Guided Evolutionary Merge"

Mar 31

• 15

Introducing WM Bench: A Benchmark for Cognitive Intelligence in World Models

Mar 29

• 13

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

Mar 10

• 38

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

Mar 9

• 16

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Mar 8

• 12

Do Bubbles Form When Tens of Thousands of AIs Simulate Capitalism?

Feb 24

• 17

FINAL Bench: The Real Bottleneck to AGI Is Self-Correction

Feb 21

• 20

View all articles

FINAL-Bench 's Spaces 36

FINCHAL Financial Forecasting Challenge

🏁

AI vs human trading contest. $2,000. NVDA, BTC, gold, oil

Open Discovery Challenge

🧬

Neglected-disease drug leaderboard for AI-designed molecules

POCKET-26B vs Bonsai · CPU (Gemma4-based)

⚔

BONSAI vs POCKET — 26B Gemma4 MoE out-runs a 27B on CPU

POCKET vs Bonsai · CPU

⚔

BONSAI vs POCKET — 35B MoE out-runs the top 1-bit 27B on CPU

Aether-7B-5Attn — 100% Open-source Foundation Model: Sovereign AI

🌏

100% open-source sovereign foundation model (Apache-2.0)

VKIE — VIDRAFT Kernel Inference Engine

🚄

VKIE (비키) — VKAE accelerates, VKUE saves, VKIE maximizes

VKUE Efficiency Leaderboard

🌐

Serve frontier-class models on minimal hardware — VKUE

AX Diagnostic Leaderboard

🩺

LLM AX diagnostic leaderboard across 7 axes

Model Galaxy

🌌

Darwin family + 2026 trending models on the HF galaxy

PROMETHEUS v1.0 — World Model Interactive Demo

🔥

World-first embodied AI world model

LEADBOARD - ADMET, Kinase and Toxicity Prediction Benchmark

🎯

Benchmark for drug prediction tools - ADMET, kinase, tox

Open Materials Challenge

🔋

Solid-state electrolyte leaderboard

AX-Ray Leaderboard

🩻

AI/AX Safety Diagnostics and Assessment

FINAL-Bench Quantum Leaderboard

⚛

Neutral quantum-method benchmark — QEC decoders & more

POCKET-Image Studio

🖼

Perfect text in any language, in any image

Darwin 9B NEG

🧬

Darwin-9B-NEG reasoning model — API-served chat demo

Darwin-35B-A3B-Opus API

🧬

OpenAI-compatible FastAPI for Darwin-35B-A3B-Opus (INT4)

Darwin-31B-Opus

👀

gemma-4-31B-it + gemma-4-31B-it-Claude-Opus-Distill

Darwin 9B Opus

👀

The child surpassed both parents — that is evolution

Gemma-4 Multichat

👀

Gemma 4 — MoE 26B or Dense 31B, Vision, Thinking

Darwin 35B A3B Opus

👀

The child surpassed both parents — that is evolution

Darwin TTS 1.7B Cross

🦀

Darwin-TTS-1.7B-Cross

Sunset Racing Drone

🚁

Fly a 3D racing drone through a sunset track

Car Game

🏃

Race a 3D car through a sunset track

AI & ML interests

Recent Activity

Papers

Articles

Writing Down the Line Between Luck and Skill

We changed one line and the benchmark score moved 0.21 AUROC

Who Tells You Whether the Molecule Your AI Just Designed Is Any Good?

AX-Ray, Finding Causal-Leakage Defects in Two General-Purpose Public Models

The Fast Gemma Challenge: our verified-SOTA recipe, in full

POCKET: a 35-billion-parameter model that runs on your iPhone — and on your PC with no GPU

Aether-7B-5Attn: A 100% Open-Source Sovereign Foundation Model — and a Controlled Experiment in Heterogeneous Attention

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier

Adding a GPU Without Building One

Chitos: From Detection to Proof — An Autonomous Security AI That Actually Exploits

FINAL-Bench Quantum: An Open, Neutral Benchmark for Quantum-Computing Methods

Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step

Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion

"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"

Darwin V6: Diagnostic-Guided Evolutionary Model Merging

"The Child That Surpassed Both Parents Through MRI-Guided Evolutionary Merge"

Introducing WM Bench: A Benchmark for Cognitive Intelligence in World Models

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Do Bubbles Form When Tens of Thousands of AIs Simulate Capitalism?

FINAL Bench: The Real Bottleneck to AGI Is Self-Correction

Team members 1

FINAL-Bench 's Spaces 36 Sort: Recently updated

FINCHAL Financial Forecasting Challenge

Open Discovery Challenge

POCKET-26B vs Bonsai · CPU (Gemma4-based)

POCKET vs Bonsai · CPU

Aether-7B-5Attn — 100% Open-source Foundation Model: Sovereign AI

VKIE — VIDRAFT Kernel Inference Engine

VKUE Efficiency Leaderboard

AX Diagnostic Leaderboard

Model Galaxy

PROMETHEUS v1.0 — World Model Interactive Demo

LEADBOARD - ADMET, Kinase and Toxicity Prediction Benchmark

Open Materials Challenge

AX-Ray Leaderboard

FINAL-Bench Quantum Leaderboard

POCKET-Image Studio

Darwin 9B NEG

Darwin-35B-A3B-Opus API

Darwin-31B-Opus

Darwin 9B Opus

Gemma-4 Multichat

Darwin 35B A3B Opus

Darwin TTS 1.7B Cross

Sunset Racing Drone

Car Game

FINAL-Bench 's Spaces 36