UC San Diego
We track 9 benchmarks that UC San Diego made or helped make.
1 in use 8 with public code 6 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| SimplerEnv Real-to-sim replicas of Google Robot and WidowX/Bridge setups. Policies scored by success rate on pick, move, drawer and Bridge tasks. | Simulated robots | May 2024 | 80% | In use |
| CoreCognition Models answer true or false and multiple choice questions on 12 core knowledge concepts from developmental cognitive science, such as object permanence and perspective taking. | General visual questions | Oct 2024 | 74.9% | System cards only |
| RepoBench Models complete code using context retrieved from other files in the same Python or Java repository. Three tasks cover retrieval, completion and the full pipeline. | Fixing real repositories | Jun 2023 | | Dropped |
| Spider 2.0-AIFunc Agents generate SQL that uses AI functions to solve 465 tasks across 125 databases. The evaluator compares execution results with reference results. | Data science and SQL | Jul 2026 | 70.3% | Not in cards |
| MonitorBench Models work through 1,540 instances across 19 tasks in 7 categories, each built around a decision-critical factor such as a cue, a hidden goal or a required step. A monitor LLM reads the chain of thought, and the monitorability score measures how often it surfaces that factor. | Deception and alignment | Mar 2026 | 91.9% | Not in cards |
| CocoaBench Unified digital agents do long human-designed tasks that mix vision, search and coding. An automatic function checks each final output. | Web browsing | Apr 2026 | 45.1% | Not in cards |
| MemoryAgentBench Memory agents receive long inputs in chunks over many turns and are tested on accurate retrieval, test-time learning, long-range understanding and selective forgetting. It adds two new sets, EventQA and FactConsolidation. | Learning from the context | Jul 2025 | 60.6% | Not in cards |
| CLIPSep Sound Separation Models isolate a requested sound from a mixture using a text or image query. The two tests mix music or everyday sounds with interfering audio. | Audio understanding and voice | Nov 2022 | Not in cards | |
| ManiSkill3 GPU-parallel robot simulator and task suite across 12 domains for manipulation learning. Success rate per task. | Simulated robots | Oct 2024 | Not in cards |