tau-0.5B-instruct-DPOP: benchmark results
Provider: Other. Access: Open.
Unified ELO 1275 ± 21, rank #2767 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 6.97 | Accuracy (%) (5-shot) | 26.2 |
| Open Portuguese LLM - ASSIN2 RTE | 62.51 | Macro F1 (%) | 21.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.73 | MC2 (%) (0-shot) | 21.4 |
| Open Portuguese LLM - ENEM | 23.16 | Accuracy (%) | 19.6 |
| Open LLM Leaderboard v1 - MMLU | 33.92 | Accuracy (%) (5-shot) | 18 |
| Open Portuguese LLM - FaQuAD NLI | 43.97 | Macro F1 (%) | 17.1 |
| Open Portuguese LLM - OAB Exams | 25.24 | Accuracy (%) | 15.9 |
| Open Portuguese LLM - BLUEX | 21.28 | Accuracy (%) | 11.8 |
| Open LLM Leaderboard v1 - WinoGrande | 57.06 | Accuracy (%) (5-shot) | 10.3 |
| Open LLM Leaderboard v1 - HellaSwag | 43.63 | Normalized accuracy (%) (10-shot) | 8.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 28.92 | Normalized accuracy (%) (25-shot) | 8.1 |
Interactive version: theaggregate.ai/model?slug=tau-0-5b-instruct-dpop · How It Works · Data refreshed daily, snapshot 2026-09-23.