tau-1.8B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1351 ± 22, rank #2475 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 30.17 | Accuracy (%) (5-shot) | 47.3 |
| Open Portuguese LLM - FaQuAD NLI | 59.81 | Macro F1 (%) | 43.8 |
| Open LLM Leaderboard v1 - MMLU | 45.96 | Accuracy (%) (5-shot) | 24.5 |
| Open Portuguese LLM - ENEM | 26.1 | Accuracy (%) | 21.7 |
| Open Portuguese LLM - ASSIN2 RTE | 62.41 | Macro F1 (%) | 21.6 |
| Open Portuguese LLM - BLUEX | 23.5 | Accuracy (%) | 16.9 |
| Open Portuguese LLM - OAB Exams | 25.47 | Accuracy (%) | 16.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 37.2 | Normalized accuracy (%) (25-shot) | 14.6 |
| Open LLM Leaderboard v1 - HellaSwag | 60.26 | Normalized accuracy (%) (10-shot) | 14.4 |
| Open LLM Leaderboard v1 - WinoGrande | 61.09 | Accuracy (%) (5-shot) | 14.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.72 | MC2 (%) (0-shot) | 11.8 |
Interactive version: theaggregate.ai/model?slug=tau-1-8b · How It Works · Data refreshed daily, snapshot 2026-09-23.