# DEAL Source: [DEAL]() Collection index: [llms.txt]() A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Benchmarks Page 1 of 1. This is an index page, not the full collection. - [Code Generation on CodeAlpaca](): Code generation; CodeAlpaca. - [Code Generation on CodeAlpacaPy](): Code Generation; CodeAlpacaPy. - [LLM Inference on Aggregate Suite (Alpaca, CodeAlpaca, HumanEval, LiveCodeBench, Math500, MBPP, MT-Bench)](): LLM Inference; Aggregate Mean over Alpaca, CodeAlpaca, HumanEval, LiveCodeBench, Math500, MBPP, MT-Bench. - [Code Generation on CodeAlpaca 20k (NLL)](): Code Generation; CodeAlpaca 20k. - [Image Classification on MNIST-scale ideal downsampling (test)](): Image Classification; MNIST-scale ideal downsampling (test). - [Task Gradient Conflict on Sequential Fine-Tuning Suite (CodeAlpaca, LogiQA, Alpaca) (test)](): Task Gradient Conflict; Sequential Fine-Tuning Suite (CodeAlpaca, LogiQA, Alpaca) (test). - [Code Generation on MBPP, CodeAlpacaPy, HumanEval, and LiveCodeBench (Composite)](): Code Generation; Mean Across MBPP, CodeAlpacaPy, HumanEval, LiveCodeBench. - [Object Detection on Daylily-Leaf (ideal)](): Object Detection; Daylily-Leaf (ideal). - [LLM Serving on Evol-CodeAlpaca (Average Latency)](): LLM Serving; Evol-CodeAlpaca. - [LLM Serving on Evol-CodeAlpaca](): LLM Serving; Evol-CodeAlpaca. - [Virtual Sensor Estimation on District Heating Network Ideal Case (noise-free)](): Virtual Sensor Estimation; District Heating Network Ideal Case (noise-free). - [Image Manipulation Localization on DEAL 300K](): Image Manipulation Localization; DEAL 300K. - [Generated Image Detection on SatelliteDiffusion car dealership SD2 fine-tuned (test)](): Generated Image Detection; SatelliteDiffusion car dealership SD2 fine-tuned (test). - [Code Generation on CodeAlpaca (pass@1, pass@10)](): Code Generation; CodeAlpaca. - [Code Generation on CodeAlpaca (CodeBLEU/SIP/TAG/LAMP/BiSR)](): Code Generation; CodeAlpaca. - [Change Detection on DEAL-300K](): Change Detection; DEAL-300K. - [Structured OCR on ORB-En-SROIE Ideal](): Structured OCR; ORB-En-SROIE Ideal. - [Code Generation on CodeAlpaca (Score)](): Code Generation; CodeAlpaca. - [Image Classification on MNIST-scale ideal downsampling, missing scales 1.0 (test)](): Image Classification; MNIST-scale ideal downsampling, missing scales 1.0 (test). - [Image Classification on MNIST-scale non-ideal downsampling (test)](): Image Classification; MNIST-scale non-ideal downsampling (test). - [Bargaining Allocation on Deal or No Deal](): Bargaining Allocation; Deal or No Deal. - [3D Object Detection on V2X-Real Ideal Setting (No Noise) (test)](): 3D Object Detection; V2X-Real Ideal Setting (No Noise) (test). - [3D Object Detection on V2X-Real Ideal Setting](): 3D Object Detection; V2X-Real Ideal Setting. - [3D Object Detection on V2X-Real Ideal Setting (test)](): 3D Object Detection; V2X-Real Ideal Setting (test). - [LLM Inference Speedup Suite (Alpaca, CodeAlpaca, HumanEval, LiveCodeBench, Math500, MBPP, MT-Bench)](): LLM Inference; Alpaca, CodeAlpaca, HumanEval, LiveCodeBench, Math500, MBPP, and MT-Bench. - [Image Classification on STL10-scale non-ideal downsampling](): Image Classification; STL10-scale non-ideal downsampling. - [Trajectory Tracking on ASV Simulation 5 Platforms (ideal conditions no delay no disturbances)](): Trajectory Tracking; ASV Simulation 5 Platforms (ideal conditions no delay no disturbances). - [Non-Hirsch ideal construction on Non-Hirsch Ideals Construction d=4](): Non-Hirsch ideal construction; Non-Hirsch Ideals Construction d=4. - [Dou Dizhu on Dou Dizhu 100,000 duplicate deals](): Dou Dizhu; Dou Dizhu 100,000 duplicate deals. - [Surgical Peg Transfer on Ideal Environment](): Surgical Peg Transfer; Ideal Environment. - [Partner Ordering Prediction on Deal-or-No-Deal cross-domain transfer n=1695 turn snapshots](): Partner Ordering Prediction; Deal-or-No-Deal cross-domain transfer n=1695 turn snapshots. - [Medical Image Lesion Detection and Diagnosis on PI-CAI ideal scenario (fold-0 val)](): Medical Image Lesion Detection and Diagnosis; PI-CAI ideal scenario (fold-0 val). - [Steganography on LongMemEval\_s Static Environment (Ideal Symmetric Prefix)](): Steganography; LongMemEval\_s Static Environment (Ideal Symmetric Prefix). - [Gaze Estimation on RealGaze Ideal](): Gaze Estimation; RealGaze Ideal. - [Backdoor Attack on CodeAlpaca-20k (test)](): Backdoor Attack; CodeAlpaca-20k (test). - [Backdoor Attack on CodeAlpaca 20k code generation instructions](): Backdoor Attack; CodeAlpaca 20k code generation instructions. - [Skull-Face Overlay on Synthetic Dataset Exp A - Ideal](): Skull-Face Overlay; Synthetic Dataset Exp A - Ideal. - [Code Generation on CodeAlpaca (test)](): Code Generation; CodeAlpaca code-generation (test). - [Ranking Prediction on Evol-CodeAlpaca R1](): Ranking Prediction; Evol-CodeAlpaca R1. - [Ranking Prediction on Evol-CodeAlpaca Llama](): Ranking Prediction; Evol-CodeAlpaca Llama. - [Non-Hirsch ideal construction on Non-Hirsch Ideals Construction d=5](): Non-Hirsch ideal construction; Non-Hirsch Ideals Construction d=5. - [Image Classification on HCMNIST CS non-ideal (test)](): Image Classification; HCMNIST CS non-ideal (test). - [Image Classification on HCMNIST non-ideal (test)](): Image Classification; HCMNIST non-ideal (test). - [Indoor Temperature Forecasting on IDEAL Real-world (test)](): Indoor Temperature Forecasting; IDEAL Real-world (test). - [Total Load Forecasting on IDEAL Real-world (test)](): Total Load Forecasting; IDEAL Real-world (test). - [3D Mobile Robot Navigation on OmniSafe Non-ideal (Mixed Degradation)](): 3D Mobile Robot Navigation; OmniSafe Non-ideal (Mixed Degradation). - [3D Mobile Robot Navigation on OmniSafe Ideal (Fast & Stable Update)](): 3D Mobile Robot Navigation; OmniSafe Ideal (Fast & Stable Update). - [Ranking Prediction on Evol-CodeAlpaca GPT-4](): Ranking Prediction; Evol-CodeAlpaca GPT-4. - [Multi-agent coordination on Idealized agent substrate (test)](): Multi-agent coordination; Idealized agent substrate (test). - [Non-Hirsch ideal construction on Non-Hirsch Ideals Construction d=7](): Non-Hirsch ideal construction; Non-Hirsch Ideals Construction d=7. - [Non-Hirsch Ideals Construction d=6](): Non-Hirsch ideal construction; Non-Hirsch Ideals Construction d=6. - [Head Pose Tracking on BlenderProc Digital Twin Head Ideal Scenario](): Head Pose Tracking; BlenderProc Digital Twin Head Ideal Scenario. - [Skull-Face Overlay Anatomical Plausibility on Synthetic SFO Dataset Ideal noise-free frontal A](): Skull-Face Overlay Anatomical Plausibility; Synthetic SFO Dataset Ideal noise-free frontal A. - [Ball-on-plate MPC on Franka Panda Ball-on-plate MPC, Ideal Simulation](): Ball-on-plate MPC; Franka Panda Ball-on-plate MPC, Ideal Simulation. - [Behavior-cloned flip on Franka Panda Ideal Simulation](): Behavior-cloned flip; Franka Panda Behavior-cloned flip Ideal Simulation. - [Box Pushing on Franka Panda Box pushing, Ideal Simulation](): Box pushing; Franka Panda Box pushing, Ideal Simulation.