Athene-70B: benchmark results
Provider: Nexusflow. Access: Open.
Aggregate Rating 1604 ± 26, rank #970 of 10916 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| WildBench | 59.54 | WB Score Task-Macro | 100 |
| Open PL LLM - PSC (generative, 5-shot) | 98.54 | Binary F1 (%) | 97 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 70.74 | Binary F1 (%) | 96.3 |
| Open PL LLM - DYK (generative, 5-shot) | 70.98 | Binary F1 (%) | 96.1 |
| Open PL LLM - Belebele (multiple choice, 5-shot) | 91.33 | Accuracy (%) | 94.1 |
| Open PL LLM - Belebele (generative, 5-shot) | 91.22 | Accuracy (%) | 93.7 |
| Open PL LLM - PolEmo2-OUT (generative, 5-shot) | 79.55 | Accuracy (%) | 93.7 |
| Open PL LLM - PolQA Reranking (multiple choice, 5-shot) | 82.74 | Accuracy (%) | 91.2 |
| Open PL LLM - KLEJ NER (multiple choice, 5-shot) | 57.14 | Accuracy (%) | 89.8 |
| Open PL LLM - PPC (multiple choice, 5-shot) | 79.4 | Accuracy (%) | 89.3 |
| Open PL LLM - PolEmo2-IN (generative, 5-shot) | 86.01 | Accuracy (%) | 88 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 36.27 | Macro F1 (%) | 87.9 |
Interactive version: theaggregate.ai/model?slug=athene-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.