trurl-2-7B-pl-instruct_unload: benchmark results
Provider: VoiceLab. Access: Open.
Aggregate Rating 1311 ± 33, rank #8517 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.74 | MC2 (%) (0-shot) | 32 |
| Open LLM Leaderboard v1 - MMLU | 49.89 | Accuracy (%) (5-shot) | 29.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.16 | Normalized accuracy (%) (25-shot) | 28.8 |
| Open LLM Leaderboard v1 - WinoGrande | 72.3 | Accuracy (%) (5-shot) | 28.8 |
| Open LLM Leaderboard v1 - GSM8K | 7.43 | Accuracy (%) (5-shot) | 26.9 |
| Open LLM Leaderboard v1 - HellaSwag | 74.64 | Normalized accuracy (%) (10-shot) | 25.1 |
Interactive version: theaggregate.ai/model?slug=trurl-2-7b-pl-instruct-unload · How It Works · Data refreshed daily, snapshot 2026-11-08.