multimaster-7B: benchmark results
An ibivibiv multidisciplinary fine-tune of openchat/openchat-3.5-0106. The card states that trained LoRA adapters were merged back into the full model. Provider: ibivibiv. Access: Open.
Aggregate Rating 1280 ± 35, rank #8983 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 11.75 | Accuracy (%) (5-shot) | 33.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.98 | MC2 (%) (0-shot) | 29.2 |
| Open LLM Leaderboard v1 - MMLU | 46.93 | Accuracy (%) (5-shot) | 25.8 |
| Open LLM Leaderboard v1 - HellaSwag | 75 | Normalized accuracy (%) (10-shot) | 25.6 |
| Open LLM Leaderboard v1 - WinoGrande | 68.35 | Accuracy (%) (5-shot) | 22.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 41.04 | Normalized accuracy (%) (25-shot) | 17.3 |
Interactive version: theaggregate.ai/model?slug=multimaster-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.