STEMBench D
AI benchmark · Reasoning
- Built by
- Ulam
- Domains
- Reasoning
- On X
- @ulamdotai ↗
- Tier
- D why
- Snapshot
What is STEMBench?
STEMBench is a private benchmark from Ulam that scores models on STEM tasks such as engineering and astronomy.
Science mostly
“Mistral Large 4 scoring well in engineering and astronomy on Ulam’s private benchmark, STEMBench”
x.com/MistralAI/status/2111056939841163336 ↗
Who built STEMBench
Led by Ulam.
Tier D
D
Long tail: little or no usage data yet.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- no usage data
- in curated RL directories (1 pt)
On X · unclear, low buzz, from 7 posts about STEMBench in the last month
New private benchmark from Ulam, mostly noticed because Mistral cited its Large 4 results; little independent evaluation, one question about scoring method.
How we got to tier D
- Adoption: no usage data. Tier D.
- On X: unclear, low buzz. “New private benchmark from Ulam, mostly noticed because Mistral cited its Large 4 results; little independent evaluation, one question about scoring method.” No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where STEMBench sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-17 snapshot.