Best LLMs for Science — Meta
The best Meta model for science is Llama 4 Maverick, scoring 67.1% on GPQA Diamond — graduate-level physics, chemistry and biology. Llama 4 Scout (58.7%) is next.
- 1
llama-4-maverickToolsJSONVision14.3 intel · $0.200/M · 107 t/s67.1%GPQA - 2llama-4-scoutToolsJSONVision10.0 intel · $0.100/M · 121 t/s58.7%GPQA
How this is ranked
AI models ranked by GPQA Diamond — graduate-level physics, chemistry and biology questions written to be un-Googleable, so the score reflects reasoning from knowledge rather than retrieval. The best large language models for scientific research and hard-science work.
Frequently asked
What is the best Meta model for science?
The best Meta model for science is Llama 4 Maverick, scoring 67.1% on GPQA Diamond — graduate-level physics, chemistry and biology. Llama 4 Scout (58.7%) is next.
What's a good alternative to Llama 4 Maverick?
Llama 4 Scout (58.7%) is the closest alternative on this metric. See the full ranking above for the tradeoffs.
How many Meta models are there?
modelgrep tracks 8 Meta models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Llama 4 Maverick. 2 of them qualify for this ranking.