LongAlpaca-13B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1215 ± 33, rank #9512 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BABILong (NIAH, v0, 4k) | 43 | QA1–5 Mean Accuracy (%) | 28.6 |
| BABILong (NIAH, v0, 8k) | 40 | QA1–5 Mean Accuracy (%) | 26.8 |
| BABILong (NIAH, v0, 16k) | 36 | QA1–5 Mean Accuracy (%) | 22.9 |
| Open LLM Leaderboard v1 - HellaSwag | 72.03 | Normalized accuracy (%) (10-shot) | 22.3 |
| BABILong | 29.33 | Mean <=128k (%) | 20.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 42.58 | Normalized accuracy (%) (25-shot) | 18.6 |
| Open LLM Leaderboard v1 - MMLU | 34.91 | Accuracy (%) (5-shot) | 18.2 |
| BABILong (NIAH, v0, 2k) | 46 | QA1–5 Mean Accuracy (%) | 17.9 |
| Open LLM Leaderboard v1 - WinoGrande | 64.09 | Accuracy (%) (5-shot) | 16.9 |
| BABILong (NIAH, v0, 0k) | 48 | QA1–5 Mean Accuracy (%) | 12.1 |
| BABILong (NIAH, v0, 1k) | 47 | QA1–5 Mean Accuracy (%) | 6.9 |
| BABILong (NIAH, v0, 32k) | 4 | QA1–5 Mean Accuracy (%) | 6.2 |
Interactive version: theaggregate.ai/model?slug=longalpaca-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.