- Organizations
- Tsinghua University
Tsinghua University: AI benchmarks & research
Tsinghua University research groups (THUDM, THUNLP and others). Maintains MedXpertQA, OlympiadBench and OVO-Bench, and co-maintains LongBench v2 with Zhipu AI.
Maintained by Tsinghua University
5 benchmarks- LongBench v2
With Zhipu AI
LongBench v2 is a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. It consists of 503 challenging multiple-choice questions with contexts ranging from 8k to 2M words across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding.
- Leader
Beam 1.067.5%
- Models scored
- 19
- MedXpertQA
A comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning, featuring 4,460 questions spanning 17 specialties and 11 body systems. Includes both text-only and multimodal subsets with expert-level exam questions incorporating diverse medical images and rich clinical information.
- Leader
Muse Spark78.4%
- Models scored
- 12
- MedXpertQA-MM
MedXpertQA-MM is the multimodal subset of MedXpertQA, evaluating expert-level medical question answering grounded in medical images.
- Leader
Qwen3.7-Plus71.0%- Models scored
- 1
- OlympiadBench
A challenging benchmark for promoting AGI with Olympiad-level bilingual multimodal scientific problems. Comprises 8,476 math and physics problems from international and Chinese Olympiads and the Chinese college entrance exam, featuring expert-level annotations for step-by-step reasoning. Includes both text-only and multimodal problems in English and Chinese.
- Leader
QvQ-72B-Preview20.4%- Models scored
- 1
- OVOBench
OVOBench (Online Video Online Benchmark) evaluates streaming video understanding, testing a model's ability to perceive and respond to video content in real time as it unfolds.
- Leader
Seed 2.1 Pro80.7%- Models scored
- 4