Luminex-34B-v0.1: benchmark results
ConvexAI's Luminex 34B v0.1, Smaug-34B with LaserRMT applied, built on the Bagel 34B v0.2 base. Provider: ConvexAI. Released 2024-02-16. Access: Open.
Aggregate Rating 1527 ± 23, rank #691 of 1635 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - WinoGrande | 71.9 | Accuracy (%) | 98.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 73.63 | Normalized accuracy (%) (25-shot) | 97.9 |
| Open LLM Leaderboard v1 - GSM8K | 72.48 | Accuracy (%) (5-shot) | 97.9 |
| Open LLM Leaderboard v1 - MMLU | 76.55 | Accuracy (%) (5-shot) | 97.6 |
| Open Chinese LLM - ARC Challenge | 65.78 | Accuracy (%) | 96.4 |
| Open Chinese LLM - HellaSwag | 70.93 | Accuracy (%) | 95 |
| Open Chinese LLM Leaderboard | 70.29 | Official Nonzero-Task Mean (%) | 94.7 |
| Open Portuguese LLM - FaQuAD NLI | 82.27 | Macro F1 (%) | 94.1 |
| Open Chinese LLM - C-Eval Semantic | 89.85 | Accuracy (%) | 92.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 69.68 | MC2 (%) (0-shot) | 89.3 |
| Open LLM Leaderboard v1 - WinoGrande | 83.43 | Accuracy (%) (5-shot) | 88.8 |
| Open Portuguese LLM - OAB Exams | 54.49 | Accuracy (%) | 86.5 |
Interactive version: theaggregate.ai/model?slug=luminex-34b-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-05.