Uncheatable Eval

What is Uncheatable Eval?

Evaluates base language models on newly collected internet data using compression-based negative log likelihood.

Released

2026-09-23

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.27510

Uncheatable Eval paper and code

• Paper https://arxiv.org/abs/2609.27510
• Code https://github.com/Jellyfish042/uncheatable_eval

Which sources cite Uncheatable Eval?

• Uncheatable Eval

Related General AI, Language & Knowledge, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench