Benchmark RadarAI BENCHMARK PROFILE
LLMTabBench
LLMTabBench evaluates LLMs on binary tabular classification in zero- and few-shot settings, using real-world and controlled synthetic datasets to study the effect of task descriptions and examples on performance.
- Released
- 2026-05-23
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
The benchmark addresses the gap in understanding how LLMs perform on tabular data under low-data regimes, which can inform their deployment in data-scarce applications.
Motivation
Supervised classification on tabular data remains a central machine learning task, but its dependence on large labeled datasets limits its applicability in data-scarce settings.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.