XVERSE-13B-2-Chat: benchmark results
Provider: XVERSE.
Aggregate Rating 1420 ± 42, rank #5168 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE General (November 2023) - Objective Questions (OPT) | 70.84 | Score | 55 |
| LaborLawBench | 30 | Mean Task Score (%; unweighted mean of 12 labor-law task sco | 48 |
| SuperCLUE General (November 2023) - Overall | 58.31 | Score | 40 |
| SuperCLUE-Code3 (May 2024) - Overall | 30.53 | Difficulty-Weighted Score | 35.7 |
| SuperCLUE General (November 2023) - Open-Ended Questions (OPEN) | 49.95 | Score | 30 |
| SuperCLUE-Code3 - Overall | 39.39 | Score | 29.4 |
| SuperCLUE General (December 2023) - Objective Questions (OPT) | 77.87 | Score | 25.9 |
| SuperCLUE General (December 2023) - Open-Ended Questions (OPEN) | 53 | Score | 22.2 |
| SuperCLUE General (December 2023) - Overall | 60.46 | Score | 18.5 |
Interactive version: theaggregate.ai/model?slug=xverse-13b-2-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.