MDL
Olmo 3 32B Think
Allen Institute for AI
Verified against Artificial Analysis · Jul 13, 2026
Capability
52
percentile index
Price /M
$0 / $0
in / out
Context
65.5K
tokens
Avg score
36.3
10 benchmarks
AA Intelligence
6.4
index
Weights
Open
Released
Nov 20, 2025
About
Olmo 3 32B Think is a open-weights model in the Olmo family from Allen Institute for AI. Benchmarked on 10 evals, averaging 36.3.
Benchmark scores · 10
avg 36.3 — higher is betterThe research behind this model
all papers mentioning it →SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks▲ 28 on HF · May 29, 2026Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads▲ 18 on HF · Jul 1, 2026A Sovereign, Open-Source Foundation Model for German and EnglishJul 10, 2026Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMsMay 28, 2026Narrative Flattening: How Post-Training Compresses Thematic, Affective, and Stylistic Variation in LLM FictionMay 27, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0/M