Luminex-34B-v0.2: benchmark results
ConvexAI's Luminex 34B v0.2, SimpleSmaug-34B with LaserRMT applied, built on the Bagel 34B v0.2 base. Provider: ConvexAI. Released 2024-02-17. Access: Open.
Aggregate Rating 1527 ± 23, rank #690 of 1635 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 74.49 | Normalized accuracy (%) (25-shot) | 99.3 |
| Open Chinese LLM - WinoGrande | 71.9 | Accuracy (%) | 98.4 |
| Open LLM Leaderboard v1 - MMLU | 76.55 | Accuracy (%) (5-shot) | 97.6 |
| Open Chinese LLM - ARC Challenge | 65.87 | Accuracy (%) | 96.9 |
| Open LLM Leaderboard v1 - GSM8K | 71.87 | Accuracy (%) (5-shot) | 96.8 |
| Open Chinese LLM - C-Eval Semantic | 90.75 | Accuracy (%) | 96.6 |
| Open Chinese LLM - HellaSwag | 71.14 | Accuracy (%) | 96.2 |
| Open Chinese LLM Leaderboard | 70.44 | Official Nonzero-Task Mean (%) | 95 |
| Open Portuguese LLM - FaQuAD NLI | 80.54 | Macro F1 (%) | 90.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 70.21 | MC2 (%) (0-shot) | 90.1 |
| Open LLM Leaderboard v1 - WinoGrande | 83.27 | Accuracy (%) (5-shot) | 87.9 |
| Open Portuguese LLM - BLUEX | 65.79 | Accuracy (%) | 87.3 |
Interactive version: theaggregate.ai/model?slug=luminex-34b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-05.