Kan-Llama-SFT-v0.5: benchmark results
Provider: Other.
Aggregate Rating 1270 ± 33, rank #9065 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.44 | MC2 (%) (0-shot) | 37.7 |
| Open LLM Leaderboard v1 - GSM8K | 5.38 | Accuracy (%) (5-shot) | 24 |
| Open LLM Leaderboard v1 - WinoGrande | 69.69 | Accuracy (%) (5-shot) | 23.8 |
| Open LLM Leaderboard v1 - HellaSwag | 72.71 | Normalized accuracy (%) (10-shot) | 23.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 47.44 | Normalized accuracy (%) (25-shot) | 22.3 |
| Open LLM Leaderboard v1 - MMLU | 42.71 | Accuracy (%) (5-shot) | 22.1 |
Interactive version: theaggregate.ai/model?slug=kan-llama-sft-v0-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.