Falcon-H1R-7B — benchmark results
TII's 7B hybrid Transformer-Mamba2 reasoning model with a 256K context (January 2026). Provider: TII. Released 2026-01-06. Access: Open.
Unified ELO 1579 ± 24, rank #533 of 1776 rated models, from 44 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA LiveCodeBench | 72.38 | Pass@1 (%) | 83.2 |
| AA AIME 2025 | 80 | Accuracy (%) | 75 |
| AA IFBench | 54.42 | Accuracy (%) | 65.4 |
| CritPt | 0.3 | Accuracy (self-reported) | 65 |
| AA Humanity's Last Exam | 10.8 | Accuracy (%) | 64.6 |
| MathArena - SMT 2025 | 85.85 | Accuracy (%) | 60.7 |
| AA CritPt | 0.29 | Accuracy (%) | 58.7 |
| MathArena - AIME 2025 | 86.67 | Accuracy (%) | 55.6 |
| MathArena - HMMT Feb 2025 | 84.17 | Accuracy (%) | 55.4 |
| AA GPQA Diamond | 66.06 | Accuracy (%) | 45.8 |
| AA Omniscience - Science, Engineering & Mathematics | 24.3 | Accuracy (%) | 42.9 |
| AA MMLU-Pro | 72.54 | Accuracy (%) | 41.7 |
Interactive version: theaggregate.ai/model?slug=falcon-h1r-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.