Molmo 7B-D

Allen Institute for AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

9.3

10 benchmarks

AA Intelligence

3.8

index

Weights

Open

Released

Sep 25, 2024

About

Molmo 7B-D is a open-weights model in the Molmo family from Allen Institute for AI. Benchmarked on 10 evals, averaging 9.3.

Benchmark scores · 10

avg 9.3 — higher is better

MMLU-Proartificial-analysis · 2026-07

37.1

GPQA Diamondartificial-analysis · 2026-07

IFBenchartificial-analysis · 2026-07

19.7

Humanity's Last Examartificial-analysis · 2026-07

5.1

LiveCodeBenchartificial-analysis · 2026-07

3.9

SciCodeartificial-analysis · 2026-07

3.6

AA Long-Context Reasoningartificial-analysis · 2026-07

AIMEartificial-analysis · 2026-07

τ²-benchartificial-analysis · 2026-07

Terminal-Bench Hardartificial-analysis · 2026-07

Details

PublisherAllen Institute for AI

FamilyMolmo

Parameters—

License—

WeightsOpen

ReleasedSep 25, 2024

History

full ledger →

Capability over time

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

API providers

Artificial Analysis$0/M