Emu2_chat Chat: benchmark results
Provider: BAAI. Released 2023-12-22.
Aggregate Rating 1350 ± 45, rank #7714 of 10552 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CoreCognition Image + Video Permanence | 43.79 | Accuracy (%) | 68.1 |
| CoreCognition Image + Video Perspective | 33.24 | Accuracy (%) | 58 |
| CoreCognition Image + Video Spatiality | 39.58 | Accuracy (%) | 42 |
| CoreCognition Image + Video Continuity | 54.94 | Accuracy (%) | 37 |
| CoreCognition Image + Video Hierarchy | 52.99 | Accuracy (%) | 34.5 |
| CMMMU | 24.5 | Test Overall (%) | 25 |
| CoreCognition Image + Video Perceptualconstancy | 57.27 | Accuracy (%) | 23.1 |
| CoreCognition Image + Video Toolusing | 43.66 | Accuracy (%) | 22.7 |
| CoreCognition Image + Video Intuitivephysics | 45.76 | Accuracy (%) | 20.2 |
| CoreCognition Image + Video Mechanicalreasoning | 44.71 | Accuracy (%) | 18.9 |
| CoreCognition Image + Video Boundary | 64.61 | Accuracy (%) | 16.8 |
| CoreCognition Image + Video Mean | 45.67 | Accuracy (%) | 16 |
Interactive version: theaggregate.ai/model?slug=emu2-chat-chat · How It Works · Data refreshed daily, snapshot 2026-11-16.