alpaca-dragon-72B-v1: benchmark results
An ibivibiv fine-tune of abacusai/Smaug-72B-v0.1 using an Alpaca-style planning and reasoning dataset. The card credits Abacus.AI and links the upstream license. Provider: ibivibiv. Access: Open.
Aggregate Rating 1526 ± 34, rank #2004 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 77.63 | Accuracy (%) (5-shot) | 99.4 |
| Open LLM Leaderboard v1 - WinoGrande | 86.03 | Accuracy (%) (5-shot) | 98.9 |
| Open LLM Leaderboard v1 - MMLU | 77.4 | Accuracy (%) (5-shot) | 98.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 73.89 | Normalized accuracy (%) (25-shot) | 98.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 72.69 | MC2 (%) (0-shot) | 93.7 |
| Open LLM Leaderboard v1 - HellaSwag | 88.16 | Normalized accuracy (%) (10-shot) | 89.9 |
Interactive version: theaggregate.ai/model?slug=alpaca-dragon-72b-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.