CORe
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Domain-Incremental Learning | CORe50 | Avg Accuracy (A)99.5 | 108 | |
| Downstream Performance Evaluation | CORE | CORE Score19.94 | 53 | |
| Few-Shot Class-Incremental Learning | CORe50 | BCR99.9 | 39 | |
| Cross-modal geo-localization | CORE Intercontinental-level Subset3 1.0 | R@164.38 | 28 | |
| Cross-modal geo-localization | CORE Intercontinental-level Subset1 1.0 | R@177.44 | 28 | |
| Cross-modal geo-localization | CORE Intercontinental-level Subset4 1.0 | R@151.35 | 15 | |
| Cross-modal geo-localization | CORE Intercontinental-level Subset2 1.0 | R@164.74 | 15 | |
| Cross-modal geo-localization | CORE World-level 1.0 (All) | R@155.84 | 15 | |
| Geo-localization | CORE Intercontinental level Subset 4 | R@172.14 | 13 | |
| Geo-localization | CORE Intercontinental level Subset 2 | R@180.03 | 13 | |
| Geo-localization | CORE (Global level (All)) | R@173.28 | 13 | |
| Reasoning | CORE-Ext | Accuracy15.9 | 10 | |
| Reasoning | CORE | Accuracy26.83 | 10 | |
| Key Extraction / Certificate Generation | Core Desktop: Intel i5-14600KF | Extraction Latency (µs)10.73 | 9 | |
| Language Modeling | Core-Extended | Score17.08 | 8 | |
| Language Modeling | Core | Score28.44 | 8 | |
| Relation Classification | CORE | F1-Mic80 | 8 | |
| General Language Understanding | CORE | CORE Score26.32 | 4 | |
| Comprehensive Optimization and Reasoning Evaluation | CORE | CORE Score25.14 | 4 | |
| Control-Dependency / Trace extraction | CoRe Lite Control-Dependency Trace subtask n=489 | F1 Score94.58 | 3 | |
| Latent centroid displacement prediction | Core Level 5 approximation | Observed Displacement6.39 | 3 |
Showing 21 of 21 rows