BLUEX v2 Benchmark

What is BLUEX v2?

BLUEX v2 evaluates large language models on open-ended, discursive questions from the second-phase entrance exams of UNICAMP and USP (2022–2025). The dataset…

Released

2026-06-21

Evaluates

Language & Knowledge, Mathematics & Formal Science, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.22723

BLUEX v2 paper, code and dataset

• Paper https://arxiv.org/abs/2606.22723
• Code https://github.com/TropicAI-Research/BLUEXv2
• Dataset https://huggingface.co/datasets/Tropic-AI/BLUEX-v2

Which sources cite BLUEX v2?

• BLUEX v2

Related Language & Knowledge, Mathematics & Formal Science, cs.CL benchmarks

• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• ActiveSciBench
• AdaMem-Bench
• AdaPlanBench
• AdvancedMathBench