BLIP-2-FLAN-T5-XXL: benchmark results
Provider: Other.
Aggregate Rating 1338 ± 45, rank #7946 of 10489 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CoreCognition Image only Spatiality | 63.64 | Accuracy (%) | 78.9 |
| CoreCognition Image only Mechanicalreasoning | 55.11 | Accuracy (%) | 77 |
| CoreCognition Image only Hierarchy | 60.52 | Accuracy (%) | 75.7 |
| ChartBench - Chart Recognition | 60.05 | Acc+ (%) | 70 |
| CoreCognition Image only Intentionality | 68.49 | Accuracy (%) | 60.5 |
| CoreCognition Image only Continuity | 58.98 | Accuracy (%) | 52.6 |
| CoreCognition Image only Boundary | 70.6 | Accuracy (%) | 48 |
| CoreCognition Image only Toolusing | 91.81 | Accuracy (%) | 47.4 |
| CoreCognition Image only Perspective | 33.73 | Accuracy (%) | 44.7 |
| ChartBench | 16.7 | Five-task average, Acc+ and NumberQA (%) | 40 |
| CoreCognition Image only Intuitivephysics | 50.86 | Accuracy (%) | 38.2 |
| SpatiaLQA - Content F1 | 51.3 | Step-content F1 (%, 0-100): harmonic mean of the pooled reca | 37.5 |
Interactive version: theaggregate.ai/model?slug=blip-2-flan-t5-xxl · How It Works · Data refreshed daily, snapshot 2026-11-20.