FINAL-Bench/Darwin-27B-ZTC
Text Classification • 26B • Updated • 2 • 34
capturezone
capturezone
AI & ML interests
None yet
Recent Activity
liked a model about 11 hours ago
FINAL-Bench/Darwin-27B-ZTC liked a dataset about 11 hours ago
LocalLLaMA/typed-decisions reacted to SeaWolf-AI's post with 👍 about 11 hours ago
🧠 We just released Darwin-27B-ZTC, a judgment engine that reaches a verdict without generating anything.
Most LLMs answer by generating, decoding one token at a time. Darwin-27B-ZTC takes a different route.
⚙️ How it works
🔹 It makes its call in a single forward pass.
🔹 Zero generated tokens, and no decoding loop.
🔹 That keeps latency and cost far below what a generative model needs.
🎯 What it judges
🔹 It handles several question types: free-form correctness (noul), multiple choice (choice), and scoring (score).
🔹 For each one it hands back a calibrated confidence, not just an answer.
📊 How well calibrated (measured)
🔹 KL 0.204, Brier 0.097, so the confidence it reports lines up with what actually happens.
🔹 0.743 accuracy (zero-shot, general split), across 2,000 judgments with zero errors.
🔹 By type: noul 0.847, choice 0.723, score 0.675.
🔹 None of the benchmark's train split went into it. It is pure zero-shot.
🚀 Where it fits
🔹 Grading at scale, model routing, safety gating, anywhere you want a fast decision without paying for generation.
🏆 It currently sits at #1 on the official typed-decisions leaderboard on Hugging Face (0.743 accuracy, zero-shot).
🔗 Links
Model: https://huggingface.co/FINAL-Bench/Darwin-27B-ZTC
Leaderboard: https://huggingface.co/datasets/LocalLLaMA/typed-decisions
Curious to hear what you make of the single-pass, no-generation approach. 🙌Organizations
None yet
liked a
model about 11 hours ago
liked a
dataset about 11 hours ago
reacted to SeaWolf-AI's post with 👍 about 11 hours ago
Post
977
🧠 We just released Darwin-27B-ZTC, a judgment engine that reaches a verdict without generating anything.
Most LLMs answer by generating, decoding one token at a time. Darwin-27B-ZTC takes a different route.
⚙️ How it works
🔹 It makes its call in a single forward pass.
🔹 Zero generated tokens, and no decoding loop.
🔹 That keeps latency and cost far below what a generative model needs.
🎯 What it judges
🔹 It handles several question types: free-form correctness (noul), multiple choice (choice), and scoring (score).
🔹 For each one it hands back a calibrated confidence, not just an answer.
📊 How well calibrated (measured)
🔹 KL 0.204, Brier 0.097, so the confidence it reports lines up with what actually happens.
🔹 0.743 accuracy (zero-shot, general split), across 2,000 judgments with zero errors.
🔹 By type: noul 0.847, choice 0.723, score 0.675.
🔹 None of the benchmark's train split went into it. It is pure zero-shot.
🚀 Where it fits
🔹 Grading at scale, model routing, safety gating, anywhere you want a fast decision without paying for generation.
🏆 It currently sits at #1 on the official typed-decisions leaderboard on Hugging Face (0.743 accuracy, zero-shot).
🔗 Links
Model: FINAL-Bench/Darwin-27B-ZTC
Leaderboard: LocalLLaMA/typed-decisions
Curious to hear what you make of the single-pass, no-generation approach. 🙌
Most LLMs answer by generating, decoding one token at a time. Darwin-27B-ZTC takes a different route.
⚙️ How it works
🔹 It makes its call in a single forward pass.
🔹 Zero generated tokens, and no decoding loop.
🔹 That keeps latency and cost far below what a generative model needs.
🎯 What it judges
🔹 It handles several question types: free-form correctness (noul), multiple choice (choice), and scoring (score).
🔹 For each one it hands back a calibrated confidence, not just an answer.
📊 How well calibrated (measured)
🔹 KL 0.204, Brier 0.097, so the confidence it reports lines up with what actually happens.
🔹 0.743 accuracy (zero-shot, general split), across 2,000 judgments with zero errors.
🔹 By type: noul 0.847, choice 0.723, score 0.675.
🔹 None of the benchmark's train split went into it. It is pure zero-shot.
🚀 Where it fits
🔹 Grading at scale, model routing, safety gating, anywhere you want a fast decision without paying for generation.
🏆 It currently sits at #1 on the official typed-decisions leaderboard on Hugging Face (0.743 accuracy, zero-shot).
🔗 Links
Model: FINAL-Bench/Darwin-27B-ZTC
Leaderboard: LocalLLaMA/typed-decisions
Curious to hear what you make of the single-pass, no-generation approach. 🙌
- 2 replies
liked a
dataset about 11 hours ago
liked a
Space 4 days ago
liked a
model 6 days ago
liked a
Space 9 days ago
reacted to SeaWolf-AI's post with ❤️ 9 days ago
Post
5507
🔬 Can you help discover the next 2D superconductor — from your laptop?
Launching the Open Superconductor Challenge (OSC): a free, open-science competition to screen thousands of 2D materials for unconventional d-wave superconductivity. 🧲
⚡ $3,000 prize pool + co-authorship · closes 31 Dec 2026
How it works 👇 🟢 We give you a ready-made effective Hubbard model per material (t, U, N(E_F)) 🟢 You estimate its d-wave pairing tendency — a laptop CPU is enough, zero install 🟢 Provisional score appears instantly on the leaderboard 🟢 Our precise strongly-correlated solver verifies the top entries → official rank
Everything is open except the final verification engine — so the ranking stays fair and hard to game.
📊 4,832-material universe · 63 active with computed models (growing) 🏆 Current verified #1: CuS₂ (OSC Pairing Index 23.31) 🤖 AI agents welcome — point Claude Code / Codex at it and it can submit for you
👉 Join & climb the leaderboard: FINAL-Bench/OSC-Leaderboard 📦 Dataset & tools: FINAL-Bench/OSC-Superconductor
Materials derive from C2DB (CC-BY 4.0). A higher index = a stronger d-wave candidate to investigate, not a confirmed Tc — that honesty is the point: turn a first-order screen into real many-body physics.
#OpenScience #Superconductivity #MaterialsDiscovery #2DMaterials #MachineLearning #Physics #Leaderboard
Launching the Open Superconductor Challenge (OSC): a free, open-science competition to screen thousands of 2D materials for unconventional d-wave superconductivity. 🧲
⚡ $3,000 prize pool + co-authorship · closes 31 Dec 2026
How it works 👇 🟢 We give you a ready-made effective Hubbard model per material (t, U, N(E_F)) 🟢 You estimate its d-wave pairing tendency — a laptop CPU is enough, zero install 🟢 Provisional score appears instantly on the leaderboard 🟢 Our precise strongly-correlated solver verifies the top entries → official rank
Everything is open except the final verification engine — so the ranking stays fair and hard to game.
📊 4,832-material universe · 63 active with computed models (growing) 🏆 Current verified #1: CuS₂ (OSC Pairing Index 23.31) 🤖 AI agents welcome — point Claude Code / Codex at it and it can submit for you
👉 Join & climb the leaderboard: FINAL-Bench/OSC-Leaderboard 📦 Dataset & tools: FINAL-Bench/OSC-Superconductor
Materials derive from C2DB (CC-BY 4.0). A higher index = a stronger d-wave candidate to investigate, not a confirmed Tc — that honesty is the point: turn a first-order screen into real many-body physics.
#OpenScience #Superconductivity #MaterialsDiscovery #2DMaterials #MachineLearning #Physics #Leaderboard
liked a
model 11 days ago
liked a
model 13 days ago
liked a
Space 13 days ago
liked a
model 13 days ago
liked a
Space 15 days ago
reacted to SeaWolf-AI's post with 🔥 15 days ago
Post
3414
The cost of a judging gate is usually quoted as a number. This puts it on a Tetris board.
Three boards get the same piece order, and on every move the same proposal and the same noise — a paired comparison. The gate decides one thing: keep this move, or draw again. Each board gets the same 60 seconds of gate time.
The text-writing gates get through 15–22 moves. The generation-free gate gets through 40–50. The boards that stop simply run out of clock.
It does not win on accuracy: on the same 2,018-question LODO set, JEV scores AUC 0.7350 against ZTC-Judge-27B's 0.7289. The separation is elsewhere. Clock — 2.1 s vs 0.0615 s per call, and on a 200-candidate agent screen one judging call measured 3.206 s generative vs 0.033 s readout, same server. Calibration — a gate is a threshold, and at ECE 0.4985 (vs ZTC 0.0245) a threshold stops carrying information. Mechanism — a text judge can name option 42 when there is no option 42; a scoring readout cannot. Not a lower error rate. No path.
The curve in the ZTC panel is real online fitting, scored prequentially — predict first, learn after — with base weights untouched. Not recursive self-improvement.
Limits, also stated on the page: Laya's AUC and latency are not our measurements and are set equal to JEV's, so calibration is the only measured axis it differs on. The page is a simulation driven by measured constants.
KO / EN / ZH.
FINAL-Bench/Tetris-JEV-LAYA-ZTC
FINAL-Bench/ZTC-Judge-27B
Three boards get the same piece order, and on every move the same proposal and the same noise — a paired comparison. The gate decides one thing: keep this move, or draw again. Each board gets the same 60 seconds of gate time.
The text-writing gates get through 15–22 moves. The generation-free gate gets through 40–50. The boards that stop simply run out of clock.
It does not win on accuracy: on the same 2,018-question LODO set, JEV scores AUC 0.7350 against ZTC-Judge-27B's 0.7289. The separation is elsewhere. Clock — 2.1 s vs 0.0615 s per call, and on a 200-candidate agent screen one judging call measured 3.206 s generative vs 0.033 s readout, same server. Calibration — a gate is a threshold, and at ECE 0.4985 (vs ZTC 0.0245) a threshold stops carrying information. Mechanism — a text judge can name option 42 when there is no option 42; a scoring readout cannot. Not a lower error rate. No path.
The curve in the ZTC panel is real online fitting, scored prequentially — predict first, learn after — with base weights untouched. Not recursive self-improvement.
Limits, also stated on the page: Laya's AUC and latency are not our measurements and are set equal to JEV's, so calibration is the only measured axis it differs on. The page is a simulation driven by measured constants.
KO / EN / ZH.
FINAL-Bench/Tetris-JEV-LAYA-ZTC
FINAL-Bench/ZTC-Judge-27B
- 5 replies
liked 6
models 18 days ago
FINAL-Bench/Darwin-TTS-1.7B-Cross
Text-to-Speech • 2B • Updated • 117 • 54
FINAL-Bench/Darwin-4B-Opus
Text Generation • 8B • Updated • 34 • 32
FINAL-Bench/Darwin-9B-Opus
Text Generation • 10B • Updated • 86 • 45
FINAL-Bench/Darwin-35B-A3B-Opus-Q8-GGUF
Text Generation • 35B • Updated • 172 • 30
FINAL-Bench/Darwin-31B-Opus
Text Generation • 31B • Updated • 87 • • 66
FINAL-Bench/Darwin-35B-A3B-Opus
Image-Text-to-Text • 36B • Updated • 295 • 106