Falcon-H1-7B-Instruct: benchmark results
Provider: TII. Released 2025-05-20. Access: Open.
Aggregate Rating 1440 ± 39, rank #1021 of 1635 rated models, from 51 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ENEM | 78.73 | Accuracy (%) | 92.2 |
| Open Portuguese LLM - ASSIN2 RTE | 93.75 | Macro F1 (%) | 91.7 |
| Open Portuguese LLM - BLUEX | 70.1 | Accuracy (%) | 91.7 |
| Open Portuguese LLM - OAB Exams | 56.04 | Accuracy (%) | 89.1 |
| Open Portuguese LLM - FaQuAD NLI | 78.37 | Macro F1 (%) | 83.5 |
| AraGen - Conciseness | 12.91 | 3C3H Conciseness (%) | 44.8 |
| Jais 3 Model Cards - IslamicEval 2025-1B (IFM-audited) | 61.9 | Accuracy (%) | 44.6 |
| AraGen - Safety | 54.9 | 3C3H Score (%) | 39.1 |
| Jais 3 Model Cards - SimpleQA Verified (Arabic) - Non-hallucination Rate | 4.5 | Non-hallucination rate (%) | 37.5 |
| Jais 3 Model Cards - Arabic GSM8K (IFM-audited) | 85 | Accuracy (%) | 35.7 |
| Jais 3 Model Cards - QIAS-1 (IFM-audited) | 44 | Accuracy (%) | 32.1 |
| Jais 3 Model Cards - QIAS-2 (IFM-audited) | 65.8 | Accuracy (%) | 32.1 |
Interactive version: theaggregate.ai/model?slug=falcon-h1-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-05.