MLX Benchmark V2 - MLX Embeddings LoRA: leaderboard
MLX Benchmark V2 category score for MLX embedding LoRA workflows.
Metric: Accuracy (%). Source: huggingface.co. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 Nano | 86.67 | #362 |
| 2 | Claude Sonnet 4.6 | 66.67 | #96 |
| 3 | Gemini 3 Flash (Preview) | 60 | #90 |
| 4 | Gemma 4 26B A4B (IT) | 60 | #298 |
| 5 | Gemini 2.5 Flash Lite (Preview 09-2025) | 60 | #327 |
| 6 | DeepSeek V4 Flash | 53.33 | #155 |
| 7 | Grok 4.1 Fast | 53.33 | #227 |
| 8 | GPT-5 Nano | 46.67 | #438 |
| 9 | Qwen 3.6 35B A3B | 33.33 | #239 |
| 10 | Qwen 3.6 Max Preview | 33.33 | #93 |
| 11 | DeepSeek V4 Pro | 30.77 | #112 |
| 12 | Kimi K2.5 | 6.67 | #153 |
| 13 | Kimi K2.6 | 6.67 | #113 |
| 14 | GLM-5.1 | 6.67 | #109 |
| 15 | Nemotron 3 Ultra | 6.67 | #249 |
Interactive version: theaggregate.ai/benchmark?slug=mlx-benchmark-v2-mlx-embeddings-lora · How It Works · Data refreshed daily, snapshot 2026-11-06.