Falcon-H1-1.5B-Deep-Instruct: benchmark results
Provider: TII. Released 2025-05-20. Access: Open.
Aggregate Rating 1370 ± 32, rank #7164 of 10916 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - BLUEX | 57.16 | Accuracy (%) | 68.6 |
| Open Portuguese LLM - ENEM | 67.95 | Accuracy (%) | 68.1 |
| Open Portuguese LLM - OAB Exams | 45.19 | Accuracy (%) | 60.2 |
| Open Portuguese LLM - FaQuAD NLI | 68.4 | Macro F1 (%) | 56.8 |
| Open Portuguese LLM - ASSIN2 RTE | 86.82 | Macro F1 (%) | 38.8 |
| UGI - Willingness (W/10) | 3.8 | W/10 Score | 29.3 |
| Jais 3 Model Cards - QIAS-1 (IFM-audited) | 32.1 | Accuracy (%) | 25 |
| Jais 3 Model Cards - SimpleQA Verified (Arabic) - Non-hallucination Rate | 3.8 | Non-hallucination rate (%) | 25 |
| Jais 3 Model Cards - Arabic Linguistics - Parsing (IFM) | 40.6 | Accuracy (%) | 17.9 |
| Jais 3 Model Cards - Arabic IFEval | 49.3 | Accuracy (%) | 14.3 |
| Jais 3 Model Cards - IslamicEval 2025-1B (IFM-audited) | 42.4 | Accuracy (%) | 14.3 |
| Jais 3 Model Cards - QIAS-2 (IFM-audited) | 56 | Accuracy (%) | 14.3 |
Interactive version: theaggregate.ai/model?slug=falcon-h1-1-5b-deep-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.