Falcon-H1-34B-Instruct: benchmark results
Provider: TII. Released 2025-05-20. Access: Open.
Aggregate Rating 1534 ± 38, rank #658 of 1635 rated models, from 48 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - BLUEX | 78.3 | Accuracy (%) | 97.4 |
| Open Portuguese LLM - FaQuAD NLI | 83.79 | Macro F1 (%) | 97.3 |
| Open Portuguese LLM - ENEM | 83.55 | Accuracy (%) | 96.8 |
| Open Portuguese LLM - OAB Exams | 64.05 | Accuracy (%) | 96.4 |
| Open Portuguese LLM - ASSIN2 RTE | 94.2 | Macro F1 (%) | 95.2 |
| AraGen - Conciseness | 29.24 | 3C3H Conciseness (%) | 76.1 |
| Jais 3 Model Cards - AraGen v3 - Conciseness | 19.7 | 3C3H Conciseness (%) | 60.7 |
| Jais 3 Model Cards - IslamicEval 2025-1B (IFM-audited) | 70.1 | Accuracy (%) | 60.7 |
| AraGen | 45.74 | 3C3H Score (%) | 60.3 |
| Jais 3 Model Cards - SimpleQA Verified (Arabic) - F-score | 6.6 | F-score (%) | 57.1 |
| Jais 3 Model Cards - Arabic GSM8K (IFM-audited) | 90.2 | Accuracy (%) | 53.6 |
| Jais 3 Model Cards - QIAS-2 (IFM-audited) | 73.4 | Accuracy (%) | 53.6 |
Interactive version: theaggregate.ai/model?slug=falcon-h1-34b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-05.