Llama 3 8B Instruct MergeSLERP Gradient1048kIO OpenBioLLM: benchmark results
Provider: Meta.
Aggregate Rating 1374 ± 34, rank #7038 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 60.54 | Accuracy (%) (5-shot) | 48.6 |
| Open LLM Leaderboard v1 - GSM8K | 30.63 | Accuracy (%) (5-shot) | 47.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.87 | Normalized accuracy (%) (25-shot) | 41.2 |
| Open LLM Leaderboard v1 - HellaSwag | 80.24 | Normalized accuracy (%) (10-shot) | 40.4 |
| Open LLM Leaderboard v1 - WinoGrande | 73.09 | Accuracy (%) (5-shot) | 31 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.4 | MC2 (%) (0-shot) | 10.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-mergeslerp-gradient1048kio-openbiollm · How It Works · Data refreshed daily, snapshot 2026-11-08.