Olmo 3.1 32B Instruct

Allen Institute for AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

19.4

7 benchmarks

AA Intelligence

6.5

index

Weights

Open

Released

Jan 13, 2026

About

Olmo 3.1 32B Instruct is a open-weights model in the Olmo family from Allen Institute for AI. Benchmarked on 7 evals, averaging 19.4.

Benchmark scores · 7

avg 19.4 — higher is better

GPQA Diamondartificial-analysis · 2026-07

53.9

IFBenchartificial-analysis · 2026-07

39.2

τ²-benchartificial-analysis · 2026-07

21.3

SciCodeartificial-analysis · 2026-07

16.7

Humanity's Last Examartificial-analysis · 2026-07

4.9

Terminal-Bench Hardartificial-analysis · 2026-07

AA Long-Context Reasoningartificial-analysis · 2026-07

The research behind this model

all papers mentioning it →

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads▲ 18 on HF · Jul 1, 2026

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details

PublisherAllen Institute for AI

FamilyOlmo

Parameters—

License—

WeightsOpen

ReleasedJan 13, 2026

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$0/M