Kyllene-34B-v1.1: benchmark results
A MergeMonster roleplay merge released by TeeZee combining Bagel-DPO, Nous-Capybara, Nous-Hermes-2-Yi and SUS-Chat 34B releases with an extended RPG preset. Provider: TeeZee. Access: Open.
Aggregate Rating 1499 ± 38, rank #2372 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 77.16 | Accuracy (%) (5-shot) | 98.3 |
| Open LLM Leaderboard v1 - WinoGrande | 83.58 | Accuracy (%) (5-shot) | 89.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.77 | Normalized accuracy (%) (25-shot) | 81.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 62.95 | MC2 (%) (0-shot) | 79.9 |
| Open LLM Leaderboard v1 - HellaSwag | 84.98 | Normalized accuracy (%) (10-shot) | 70.6 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=kyllene-34b-v1-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.