UT Austin
We track 8 benchmarks that UT Austin made or helped make.
0 in use 8 with public code 8 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| PutnamBench Models write formal Lean proofs of Putnam competition problems. A proof counts only when the verifier accepts it. | Formal proofs | Jul 2024 |  87.5% | Fading |
| LIBERO Simulated Franka tabletop tasks in four 10-task suites. Policies fine-tuned on 50 demos per task. Success rate over ~50 trials. | Simulated robots | Jun 2023 |  97.2% | Fading |
| MuSR Models answer questions about long generated narratives such as murder mysteries, object placement and team allocation. Each item needs several soft reasoning steps over the story. | Language reasoning | Oct 2023 |  86.7% | Fading |
| ChartMuseum Models answer 1,162 expert-annotated questions about real-world charts from 184 sources. Many questions need visual reasoning that text cannot replace. | Documents, charts and text in images | May 2025 |  80.7% | Fading |
| RoboCasa GR1 Tabletop Tasks A simulated Fourier GR-1 humanoid with dexterous hands does 24 tabletop pick-and-place tasks, including unseen object and container pairs. Success rate per task. | Simulated robots | Mar 2025 |  50% | Fading |
| RoboCasa Simulated mobile manipulators and humanoids do 100 kitchen tasks, 25 atomic and 75 composite, across 120 scenes. Scored by success rate. | Simulated robots | Jun 2024 | 70.8% | Fading |
| LLM-AggreFact Models judge whether claims are supported by a grounding document across 11 pooled datasets, such as RAGTruth and ExpertQA. Scored by balanced accuracy. | Faithful to sources | Apr 2024 | 75.9% | Not in cards |
| RoboCasa365 Mobile-manipulator kitchen sim: train on 300-task Human300 data, test on 50 tasks incl. 16 unseen composite tasks. Success rate. | Simulated robots | Mar 2026 | 23.9% | Not in cards |