MDL
Olmo 3 7B Instruct
Allen Institute for AI
Verified against Artificial Analysis · Jul 13, 2026
Capability
37
percentile index
Price /M
$0.1 / $0.2
in / out
Context
—
Avg score
22.2
10 benchmarks
AA Intelligence
2.8
index
Weights
Open
Released
Nov 20, 2025
About
Olmo 3 7B Instruct is a open-weights model in the Olmo family from Allen Institute for AI. Benchmarked on 10 evals, averaging 22.2.
Benchmark scores · 10
avg 22.2 — 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.
Performance & price
Price in / out$0.1 / $0.2 per 1M
Blended price$0.125 / 1M
Math index41.3
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.2/M