Lumina-3.5: benchmark results
Provider: Ppoyaa. Released 2025-07-01. Access: Open.
Aggregate Rating 1457 ± 38, rank #3482 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 75.66 | MC2 (%) (0-shot) | 95.7 |
| Open LLM Leaderboard v1 - HellaSwag | 88.82 | Normalized accuracy (%) (10-shot) | 94.2 |
| Open LLM Leaderboard v1 - WinoGrande | 83.98 | Accuracy (%) (5-shot) | 91.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.59 | Normalized accuracy (%) (25-shot) | 89.6 |
| Open LLM Leaderboard v1 - GSM8K | 67.93 | Accuracy (%) (5-shot) | 84.7 |
| Open Medical LLM - MMLU College Medicine | 67.05 | Accuracy (%) | 81.5 |
| Open LLM Leaderboard v1 - MMLU | 64.48 | Accuracy (%) (5-shot) | 71.1 |
| Open Medical LLM - MMLU Clinical Knowledge | 70.94 | Accuracy (%) | 48.7 |
| Open Medical LLM - MMLU Anatomy | 59.26 | Accuracy (%) | 45.3 |
| Open Medical LLM - PubMedQA | 73.6 | Accuracy (%) | 44 |
| Open Medical LLM | 63.72 | Average Accuracy (%) | 40.1 |
| Open Medical-LLM Leaderboard (BenchmarkList) | 63.72 | Medical average (%) | 40 |
Interactive version: theaggregate.ai/model?slug=lumina-3-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.