d1-3B beats Vega 4B: 3.4x faster with +7.2pp accuracy on M4 Max
JosephJacks_ · x · 2026-10-17
Developer nathanrchn benchmarked Liquid AI's d1-3B against Vega 4B on an Apple M4 Max: 3.4x faster, more accurate, with fewer parameters. The chart, based on Vega's 43-task public suite with 2,535 identical API inputs, shows:
- d1-3B: 78.95% accuracy at 101.4 ms
- Vega 4B: 71.73% at 348.8 ms
- d1 omni 600M: 62.41% at 53.6 ms
- Vega 0.8B: 55.60% at 146.4 ms
d1-3B beats both Vega models on both axes, sitting on the Pareto frontier. The model is available on Hugging Face.
More from Models
- LMArena opens Code Arena WebDev for blind head-to-head model coding battles — arena · 2026-10-17
- Unverified: GPT-6 Pro said to launch parallel research subagents, 50-100 weekly messages — TheMoonMidas · 2026-10-17
- Gemini 4 Argon costs 43¢ vs Opus 5.5's $2.43 on same build prompt — MattVidPro · 2026-10-17
- Perplexity quietly retires GLM 5.3, user still used it two minutes earlier — ChrisUniverse · 2026-10-17
- NVIDIA Launches Fastino Training API: Pay Per Token for SFT and RL — NVIDIAAI · 2026-10-17
- F5 Post-Trains Nemotron for Enterprises: Frontier Accuracy at 40x Lower Cost — NVIDIAAI · 2026-10-17