cross-openhermes-llama3.8B-12288-inst: benchmark results
Provider: Other.
Aggregate Rating 1434 ± 39, rank #4496 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SeaEval - Dialogue - DialogSum (Zero-Shot) | 27.08 | Average ROUGE (0-100) | 100 |
| SeaEval - Dialogue - SAMSum (Zero-Shot) | 30.04 | Average ROUGE (0-100) | 83.3 |
| SeaEval - Emotion - IndoEmotion (Zero-Shot) | 70.45 | Accuracy (%) | 70.8 |
| SeaEval - Fundamental NLP Tasks - CoLA (Zero-Shot) | 82.07 | Accuracy (%) | 66.7 |
| SeaEval - FLORES Translation - Malay-to-English (Zero-Shot) | 39.59 | BLEU (0-100) | 65.2 |
| SeaEval - Fundamental NLP Tasks - QQP (Zero-Shot) | 79.2 | Accuracy (%) | 60.9 |
| SeaEval - FLORES Translation - Indonesian-to-English (Zero-Shot) | 39.01 | BLEU (0-100) | 58.7 |
| SeaEval - Cultural Reasoning - SG-Eval v2 Open (Zero-Shot) | 52.48 | Accuracy (%) | 56.5 |
| SeaEval - FLORES Translation - Chinese-to-English (Zero-Shot) | 24.38 | BLEU (0-100) | 56.5 |
| SeaEval - Cultural Reasoning - US-Eval (Zero-Shot) | 76.64 | Accuracy (%) | 56.2 |
| SeaEval - Fundamental NLP Tasks - QNLI (Zero-Shot) | 82.83 | Accuracy (%) | 52.2 |
| SeaEval - Fundamental NLP Tasks - RTE (Zero-Shot) | 80.51 | Accuracy (%) | 50 |
Interactive version: theaggregate.ai/model?slug=cross-openhermes-llama3-8b-12288-inst · How It Works · Data refreshed daily, snapshot 2026-11-08.