fialka-13B-v3.1: benchmark results
Provider: Other.
Aggregate Rating 1128 ± 35, rank #10379 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.03 | MC2 (%) (0-shot) | 22.3 |
| Open LLM Leaderboard v1 - GSM8K | 0.53 | Accuracy (%) (5-shot) | 12.7 |
| Open LLM Leaderboard v1 - WinoGrande | 58.48 | Accuracy (%) (5-shot) | 11.5 |
| Open LLM Leaderboard v1 - HellaSwag | 47.28 | Normalized accuracy (%) (10-shot) | 9.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 29.95 | Normalized accuracy (%) (25-shot) | 9 |
| Open LLM Leaderboard v1 - MMLU | 25.41 | Accuracy (%) (5-shot) | 8.2 |
Interactive version: theaggregate.ai/model?slug=fialka-13b-v3-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.