falcon-40B Instruct: benchmark results
Provider: TII. Released 2023-05-25. Access: Open.
Unified ELO 1347 ± 11, rank #2249 of 2656 rated models, from 75 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Mathematics | 33.33 | Accuracy (%) | 93.3 |
| MMLU-by-task - TruthfulQA MC1 | 37.7 | Accuracy (%) | 91 |
| MMLU-by-task - Anatomy | 54.07 | Accuracy (%) | 90 |
| MMLU-by-task - HellaSwag | 64.62 | Accuracy (%) | 88.1 |
| MMLU-by-task - TruthfulQA MC2 | 52.52 | Accuracy (%) | 87.6 |
| MMLU-by-task - Virology | 49.4 | Accuracy (%) | 87.4 |
| MMLU-by-task - Professional Medicine | 58.09 | Accuracy (%) | 86.9 |
| MMLU-by-task - Medical Genetics | 64 | Accuracy (%) | 86.3 |
| MMLU-by-task - Human Sexuality | 67.18 | Accuracy (%) | 86 |
| MMLU-by-task - Public Relations | 66.36 | Accuracy (%) | 85.5 |
| MMLU-by-task - College Mathematics | 37 | Accuracy (%) | 85.2 |
| MMLU-by-task - Management | 75.73 | Accuracy (%) | 84.7 |
Interactive version: theaggregate.ai/model?slug=falcon-40b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.