Seoul National University
We track 8 benchmarks that Seoul National University made or helped make.
0 in use 5 with public code 6 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| KoBALT Models answer 700 expert-written multiple-choice questions on 24 Korean linguistic phenomena in syntax, semantics, pragmatics, phonology and morphology. | Reasoning in many languages | May 2025 | 61% | Fading |
| K-Viscuit Models answer multiple-choice visual questions about Korean culture. Questions were written through human and VLM collaboration. | General visual questions | Jun 2024 | 89.5% | Fading |
| Rule2DRC Models write KLayout scripts from chip design rules. The evaluator checks whether each script flags the correct violations on every test layout. | Electronics | May 2026 | 67.9% | Not in cards |
| TutorCaseBench Tutors respond to students whose behavior interferes with learning. Case-specific rubrics grade the responses, and a separate track tests selection among possible interventions. | Other professions | Oct 2026 | 59.4% | Not in cards |
| PReMind-Bench Models inspect a scene and decide whether to retrieve a personal memory before answering. Judges check whether the answer addresses the hazard and uses the right person’s information. | Wellbeing and sycophancy | Nov 2026 | 87.3% | Not in cards |
| HumanoidToolBench Humanoid robot policies pick a suitable tool and use it, walking when needed, across 18 tasks in simulation and on a real Unitree G1. | Real robots | Oct 2026 | | Not in cards |
| ExFunTube Models explain why a moment in a short video is funny. The authors compare explanations with human references and ask viewers to rate them. | Video captioning | Jul 2023 | Not in cards | |
| Ref-YouTube-VOS Models segment and track the object that a sentence describes in YouTube-VOS videos. Scored by J&F on a server-graded validation split. | Video understanding | Aug 2020 | Not in cards |