modelgrep

Best LLMs for Science — Cohere

Match · Updated August 2026

The best Cohere model for science is North Mini Code (free), scoring 75.7% on GPQA Diamond — graduate-level physics, chemistry and biology. Command A (52.7%) is next.

75.7%GPQA
19.8Intelligence
18 t/sSpeed
FreeInput /M
256KContext
  1. 1cohere logo
    north-mini-code:free
    ReasoningTools19.8 intel · Free/M · 18 t/s
    75.7%
    GPQA
  2. 2cohere logo
    command-a
    JSON7.7 intel · $2.50/M · 47 t/s
    52.7%
    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 Cohere model for science?

The best Cohere model for science is North Mini Code (free), scoring 75.7% on GPQA Diamond — graduate-level physics, chemistry and biology. Command A (52.7%) is next.

What's a good alternative to North Mini Code (free)?

Command A (52.7%) is the closest alternative on this metric. See the full ranking above for the tradeoffs.

How many Cohere models are there?

modelgrep tracks 5 Cohere models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by North Mini Code (free). 2 of them qualify for this ranking.

More Cohere rankings

All rankings