WizardLM-2-7B (Publisher: microsoft): benchmark results
Provider: Microsoft.
Aggregate Rating 1398 ± 33, rank #6225 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 56.98 | MC2 (%) (0-shot) | 69.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.88 | Normalized accuracy (%) (25-shot) | 60.2 |
| Open LLM Leaderboard v1 - GSM8K | 43.75 | Accuracy (%) (5-shot) | 57.9 |
| Open LLM Leaderboard v1 - HellaSwag | 83.26 | Normalized accuracy (%) (10-shot) | 57.2 |
| Open LLM Leaderboard v1 - MMLU | 61.53 | Accuracy (%) (5-shot) | 52.1 |
| Open LLM Leaderboard v1 - WinoGrande | 73.56 | Accuracy (%) (5-shot) | 32.6 |
Interactive version: theaggregate.ai/model?slug=wizardlm-2-7b-publisher-microsoft · How It Works · Data refreshed daily, snapshot 2026-11-08.