WestLake-7B-v2-laser: benchmark results
QuixiAI's laser-pruned version of senseable's WestLake 7B v2, applying laserRMT to identify and adjust high-noise layers. Provider: Cognitive Computations. Released 2024-01-26. Access: Open.
Aggregate Rating 1468 ± 23, rank #882 of 1635 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 86.74 | Accuracy (%) (5-shot) | 99.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 73.29 | Normalized accuracy (%) (25-shot) | 96.7 |
| Open LLM Leaderboard v1 - HellaSwag | 88.66 | Normalized accuracy (%) (10-shot) | 93.4 |
| Open LLM Leaderboard v1 - GSM8K | 68.23 | Accuracy (%) (5-shot) | 85.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 67.04 | MC2 (%) (0-shot) | 85.4 |
| Open Chinese LLM - TruthfulQA MC | 59.03 | Accuracy (%) | 80.2 |
| Open Chinese LLM - WinoGrande | 66.06 | Accuracy (%) | 76.2 |
| Open LLM Leaderboard v1 - MMLU | 64.72 | Accuracy (%) (5-shot) | 75.5 |
| Open Portuguese LLM - ASSIN2 RTE | 91.91 | Macro F1 (%) | 72.2 |
| Open Portuguese LLM - FaQuAD NLI | 70.46 | Macro F1 (%) | 61.4 |
| Open Portuguese LLM - BLUEX | 54.66 | Accuracy (%) | 60.8 |
| Open Chinese LLM - ARC Challenge | 53.75 | Accuracy (%) | 59.9 |
Interactive version: theaggregate.ai/model?slug=westlake-7b-v2-laser · How It Works · Data refreshed daily, snapshot 2026-11-05.