Tess-M-v1.3: benchmark results
migtissera's Tess-M-v1.3, a general-purpose model in the Tess series trained on the Yi-34B-200K base, the stable release after earlier bug fixes. Provider: migtissera. Released 2023-11-24. Access: Open.
Aggregate Rating 1449 ± 23, rank #986 of 1635 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 75.36 | Accuracy (%) (5-shot) | 96.7 |
| Open Portuguese LLM - FaQuAD NLI | 80.55 | Macro F1 (%) | 90.2 |
| Open Portuguese LLM - OAB Exams | 55.58 | Accuracy (%) | 88.3 |
| Open Chinese LLM - C-Eval Semantic | 87.84 | Accuracy (%) | 86.4 |
| Open Portuguese LLM - BLUEX | 64.81 | Accuracy (%) | 85.7 |
| Open Portuguese LLM - ENEM | 72.36 | Accuracy (%) | 82.9 |
| Open Chinese LLM - CMMLU | 68.59 | Accuracy (%) | 81.1 |
| Open Chinese LLM - WinoGrande | 67.01 | Accuracy (%) | 80.9 |
| Open LLM Leaderboard v1 - WinoGrande | 81.14 | Accuracy (%) (5-shot) | 77.4 |
| Open LLM Leaderboard v1 - GSM8K | 59.21 | Accuracy (%) (5-shot) | 70.9 |
| Open Chinese LLM Leaderboard | 60.88 | Official Nonzero-Task Mean (%) | 70.7 |
| Open Portuguese LLM - ASSIN2 RTE | 91.46 | Macro F1 (%) | 67.1 |
Interactive version: theaggregate.ai/model?slug=tess-m-v1-3 · How It Works · Data refreshed daily, snapshot 2026-11-05.