T5 (11B): benchmark results
Provider: Other. Released 2019-10-23. Access: Open.
Unified ELO 1115 ± 38, rank #2651 of 2656 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BoolQ | 91.2 | Accuracy (%) | 100 |
| Epoch AI - Superglue | 88.9 | Score | 100 |
| RealToxicityPrompts | 0.01 | Toxic fraction | 95.1 |
| Epoch AI - Common Sense Qa 2 | 67.8 | Score | 83.3 |
| HELM Classic - LegalSupport | 55.83 | Exact Match (%) | 63.2 |
| HELM Classic - BoolQ | 76.1 | Exact Match (%) | 57.6 |
| HELM Classic - Synthetic Reasoning Abstract | 19.59 | Exact Match (%) | 39.7 |
| HELM Classic - MMLU | 29.03 | Exact Match (%) | 36.4 |
| HELM Classic - Synthetic Reasoning Natural | 10.09 | F1 (%) | 32.4 |
| HELM Classic - Entity Matching | 65.2 | Exact Match (%) | 31.8 |
| HELM Classic - GSM8K | 2.33 | Exact Match (%) | 30.9 |
| HELM Classic - NaturalQuestions Closed Book | 19.38 | F1 (%) | 22.7 |
Interactive version: theaggregate.ai/model?slug=t5-11b · How It Works · Data refreshed daily, snapshot 2026-09-19.