BLINKG - Schema-Aligned - Function Name: leaderboard
Metric: F1 (%; expert-validated mappings for the transformation function a value needs; 10 gold task instances; GTFS-Madrid transit CSV files mapped to the LinkedGTFS ontology; macro-average of three runs). Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 86 |
| 2 | Llama 3.3 70B Instruct | 86 |
| 3 | GPT-4o | 75 |
| 4 | O3 | 74 |
| 5 | Mixtral 8x22B Instruct | 64 |
Interactive version: theaggregate.ai/benchmark?slug=blinkg-schema-aligned-function-name · How It Works · Data refreshed daily, snapshot 2026-09-26.