Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand
cs.CL
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/nexusflowai/NexusBench
Terminology
Sources
- Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings
- AGC-Bench: Measuring Artificial General Creativity
- PaliGemma: A versatile 3B VLM for transfer
- CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
- Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
- Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge
- ACEBench: Who Wins the Match Point in Tool Usage?
- Evaluating Large Language Models Trained on Code
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- MINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo Calibration
- Fail2Drive: Benchmarking Closed-Loop Driving Generalization
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- LoRA: Low-Rank Adaptation of Large Language Models
- RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
- Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models
- DatBench: Discriminative, Faithful, and Efficient VLM Evaluations
- Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data