AI Radar
Support
LiveUpdated 2026-11-06 15:10 UTC

STEMBench

STEMBench is Mistral Large 4 scoring well in engineering and astronomy on Ulam’s private benchmark, STEMBench. It is ranked #946 on the AI Radar, in Frontier models, first seen 21 days ago and shared in 1 post (61.6k views).

Visit ulam.ai

What STEMBench says about itself

Compare AI research progress across biology, chemistry, physics, astronomy, Earth science, and engineering. STEMBench reports domain scores, run settings, and audited progress across 120 tasks.

STEMBench — Six-Domain Model Evaluation | Ulam Ulam / Scientific reasoning evaluation STEMBench . Research progress. Across six STEM domains. A correctness-first evaluation of AI research across biology, chemistry, physics, astronomy, Earth science, and engineering. Compare supported scientific progress, reproducibility, and how honestly a model states what remains unresolved. Explore domain scores ↓ How scoring works Public test set ↓ ErdosBench ↗ 120 tasks per full run 6 domains · 20 tasks each 10 runs · 1,200 scored responses 0 full-target successes across all runs 01 / Domain comparison A field-by-field view. Experimental fractional…

Alternatives to STEMBench

STEMBench in numbers

FAQ

What is STEMBench?

Mistral Large 4 scoring well in engineering and astronomy on Ulam’s private benchmark, STEMBench It was first shared on X 21 days ago and is ranked #946 on the AI Radar.

Is STEMBench free?

Pricing is not stated on the page we read.

Who shared STEMBench?

1 account on X, including @MistralAI, in 1 post totalling 61.6k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.