L3-krai-test: benchmark results
Provider: Other.
Aggregate Rating 1422 ± 36, rank #5076 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 70.36 | Accuracy (%) (5-shot) | 92.7 |
| Open LLM Leaderboard v1 - MMLU | 67.66 | Accuracy (%) (5-shot) | 89.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.09 | Normalized accuracy (%) (25-shot) | 51.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.82 | MC2 (%) (0-shot) | 49.6 |
| Open LLM Leaderboard v1 - WinoGrande | 75.22 | Accuracy (%) (5-shot) | 40.9 |
| Open LLM Leaderboard v1 - HellaSwag | 79.28 | Normalized accuracy (%) (10-shot) | 37.3 |
Interactive version: theaggregate.ai/model?slug=l3-krai-test · How It Works · Data refreshed daily, snapshot 2026-11-08.