Backpropagation on an Inference-Only NPU: Pretraining VKORE-46M-NPU From Scratch
• 13
AI & ML interests
Contact: arxivgpt@gmail.com
Recent Activity
Papers
View all Papers Articles
Organization Card
FINAL-Bench
Open, free benchmarks for science. You propose, a hidden verifier grades it, and the standings are public.
Entry is free, prize money is self funded, and the data and scoring rules are published. Open to researchers, students and AI coding agents.
Open challenges
| Challenge | Field |
|---|---|
| Open Discovery Challenge | Drug and materials discovery |
| Open Materials Challenge | Solid state battery electrolytes |
| Open Superconductor Challenge | 2D materials, d-wave pairing |
| Open Quantum Challenge | Hubbard energies, surface-code decoders |
| Leaderboard | Combined standings |
Scores are computational predictions, not laboratory measurements. A high score is a hypothesis worth testing.
Recognition
ModelScope, the Alibaba and CCF platform, certified FINAL-Bench as a Research Institution (研究机构). Maeil Business Newspaper reported it as the only Korean organization to hold that certification. The badge is granted by platform review of an organization's character and technical reliability, independent of download counts.
Open source
- quantum-bench-harness on GitHub
Follow the work
- LinkedIn: VIDraft
- GitHub: final-bench
spaces 45
pinned
Running
81
Open Discovery Challenge
🧬
Neglected-disease drug leaderboard for AI-designed molecules
pinned
Running
19
ONGRID
🌌
Ontology·Graph·Decision engine with zero-token ZTC verify
pinned
Running
36
OSC Open Superconductor Challenge
🧲
Estimate superconducting pairing of 2D materials
pinned
Running
42
FINCHAL Financial Forecasting Challenge
🏁
AI vs human trading contest. $2,000. NVDA, BTC, gold, oil
pinned
Paused
Featured
52
POCKET-26B vs Bonsai · CPU (Gemma4-based)
⚔
BONSAI vs POCKET — 26B Gemma4 MoE out-runs a 27B on CPU
pinned
Paused
47
POCKET vs Bonsai · CPU
⚔
BONSAI vs POCKET — 35B MoE out-runs the top 1-bit 27B on CPU
models 82
FINAL-Bench/VKORE-46M-NPU
Text Generation • 45.8M • Updated • 6 • 27
FINAL-Bench/Darwin-27B-ZTC-v9
Text Classification • 26B • Updated • 108 • 2
FINAL-Bench/README
Updated • 1
FINAL-Bench/Darwin-35B-ZTC-Vision
Image Classification • 35B • Updated • 6.04k • 2
FINAL-Bench/Darwin-27B-ZTC-v5
Text Classification • 26B • Updated • 116 • 6
FINAL-Bench/POCKET-Darwin-180B-GGUF
Text Generation • 177B • Updated • 187k • 64
FINAL-Bench/POCKET-26B-GGUF
Text Generation • 25B • Updated • 240k • 59
FINAL-Bench/POCKET-35B-GGUF
Text Generation • 35B • Updated • 528k • 84
FINAL-Bench/Darwin-27B-ZTC-v2
Text Classification • 26B • Updated • 128 • 37
FINAL-Bench/Darwin-27B-ZTC
Text Classification • 26B • Updated • 378 • 38
datasets 10
FINAL-Bench/OSC-Superconductor
Viewer • Updated • 6.9k • 11.8k • 39
FINAL-Bench/oqc-data
Updated • 204 • 22
FINAL-Bench/Darwin-27B-ZTC-decision-index
Updated • 66
FINAL-Bench/Darwin-27B-JEV-decision-index
Updated • 272 • 1
FINAL-Bench/AX-RAY
Viewer • Updated • 117 • 230 • 47
FINAL-Bench/Aether-7B-5Attn-checkpoints
Updated • 67 • 30
FINAL-Bench/quantum-leaderboard-assets
Viewer • Updated • 2 • 60 • 1
FINAL-Bench/World-Model
Viewer • Updated • 100 • 541 • 51
FINAL-Bench/ALL-Bench-Leaderboard
Viewer • Updated • 90 • 906 • 26
FINAL-Bench/Metacognitive
Viewer • Updated • 100 • 411 • 108