view post Post 4,129 How do I test an LLM for my unique needs?If you work in finance, law, or medicine, generic benchmarks are not enough.This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md
Article 38 Introducing harness adapters: adapt your favorite model to your harness to improve performance and cost
benchmarks meituan-longcat/LARYBench Updated Apr 30 • 6.54k • 21 llamaindex/ParseBench Benchmark • Updated Apr 19 • 169k • 48.4k • 173 nvidia/QCalEval Viewer • Updated Apr 13 • 243 • 551 • 21 allenai/olmOCR-bench Benchmark • Updated Feb 19 • 18k • 334
RULER Datasets Falcon-H1-3B-Base RULER Datasets lighteval/RULER-131072-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 51 lighteval/RULER-65536-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 54 lighteval/RULER-32768-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 57 lighteval/RULER-16384-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 36
benchmarks meituan-longcat/LARYBench Updated Apr 30 • 6.54k • 21 llamaindex/ParseBench Benchmark • Updated Apr 19 • 169k • 48.4k • 173 nvidia/QCalEval Viewer • Updated Apr 13 • 243 • 551 • 21 allenai/olmOCR-bench Benchmark • Updated Feb 19 • 18k • 334
RULER Datasets Falcon-H1-3B-Base RULER Datasets lighteval/RULER-131072-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 51 lighteval/RULER-65536-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 54 lighteval/RULER-32768-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 57 lighteval/RULER-16384-Falcon-H1-3B-Base Viewer • Updated Jun 18, 2025 • 6.5k • 36