Tess-2.0-Llama-3-8B: benchmark results
Provider: Other. Released 2024-05-05. Access: Open.
Unified ELO 1427 ± 1, rank #1042 of 1392 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 39.63 | Average Score (%) | 69.5 |
| Open Chinese LLM - WinoGrande | 63.06 | Accuracy (%) | 52.5 |
| Open Chinese LLM - CMMLU | 52.83 | Accuracy (%) | 43.9 |
| Open Chinese LLM - HellaSwag | 57.89 | Accuracy (%) | 35.6 |
| Open Chinese LLM - C-Eval Semantic | 64.06 | Accuracy (%) | 35.3 |
| Open Chinese LLM - GSM8K | 36.47 | Accuracy (%) | 32.9 |
| Open Chinese LLM - TruthfulQA MC | 51.8 | Accuracy (%) | 32.3 |
| Open Chinese LLM Leaderboard | 53.32 | Average Score (%) | 30.3 |
| Open Chinese LLM - ARC Challenge | 47.1 | Accuracy (%) | 26.3 |
Interactive version: theaggregate.ai/model?slug=tess-2-0-llama-3-8b · How It Works · Data refreshed daily, snapshot 2026-09-05.