Orca-2-13B-SFT-v4: benchmark results
Provider: Microsoft. Access: Open.
Aggregate Rating 1385 ± 33, rank #6709 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 80.03 | Accuracy (%) (5-shot) | 72 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.15 | MC2 (%) (0-shot) | 50.8 |
| Open LLM Leaderboard v1 - MMLU | 60.23 | Accuracy (%) (5-shot) | 47.3 |
| Open LLM Leaderboard v1 - GSM8K | 28.28 | Accuracy (%) (5-shot) | 45.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.22 | Normalized accuracy (%) (25-shot) | 42.4 |
| Open LLM Leaderboard v1 - HellaSwag | 79.58 | Normalized accuracy (%) (10-shot) | 38.3 |
Interactive version: theaggregate.ai/model?slug=orca-2-13b-sft-v4 · How It Works · Data refreshed daily, snapshot 2026-11-08.