Best Nous Models for Math & Science

Match · Updated July 2026

The best Nous model for math and science is Hermes 3 70B Instruct, scoring 40.1% on GPQA Diamond (graduate-level physics, chemistry and biology).

40.1%GPQA

5.1Intelligence

$0.700Input /M

131KContext

AI models ranked by GPQA Diamond — graduate-level physics, chemistry and biology questions that can't be answered by lookup. The best LLMs for math, quantitative reasoning and hard-science work.

1
hermes-3-llama-3.1-70b
JSON5.1 intel · $0.700/M · 131K ctx
40.1%
GPQA

Frequently asked

What is the best Nous model for math?

The best Nous model for math and science is Hermes 3 70B Instruct, scoring 40.1% on GPQA Diamond (graduate-level physics, chemistry and biology).

How many Nous models are there?

modelgrep tracks 4 Nous models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Hermes 3 70B Instruct. 1 of them qualify for this ranking.

More Nous rankings

Nous: Smartest LLMs Nous: Best LLMs for Coding Nous: Best LLMs for Design & Frontend Nous: Fastest LLMs Nous: Lowest-Latency LLMs Nous: Cheapest LLMs Nous: Best Free LLMs Nous: Best Reasoning LLMs Nous: Best Vision LLMs Nous: Best LLMs for Agents Nous: Best Open-Source LLMs Nous: Longest-Context LLMs Nous: Best LLMs for Writing Nous: Best LLMs for RAG Nous: Best LLMs for SQL & Data Analysis Nous: Best LLMs for Roleplay Nous: Best Uncensored LLMs

All rankings

Small & Fast LLMs Best Local LLMs Smartest LLMs Best LLMs for Coding Best LLMs for Design & Frontend Fastest LLMs Lowest-Latency LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Best Open-Source LLMs Longest-Context LLMs Best LLMs for Writing Best LLMs for RAG Best LLMs for SQL & Data Analysis Best LLMs for Roleplay Best Uncensored LLMs