Skip to content
ModelCap

Olmo 3 32B Think

Current board #75Arena #252Open weights

Allen Institute·allenai/olmo-3-32b-think

Olmo 3 32B Think is a language model published by Allen Institute. No callable OpenRouter endpoint was published in the latest snapshot. It accepts text input and returns text. The published context limit is 66K tokens. The catalogue declares support for reasoning, structured outputs.

ModelCap Index · Current board
37.5#75
Measured · 62% support · score interval 37.5–47.7
Market Gravity
8.4
Secondary market signal
Input
$0.15
per 1M tokens
Output
$0.50
per 1M tokens
Context
66K
tokens
Providers
0
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

No provider is currently serving this model.

ModelCap Index · Current board

Methodology
37.5
Measured · 2 public benchmark observations across 2 boards
Current board
#75
Public rank basis
Measured (measured)
Index support
61.6% · strong
Index interval
37.5–47.7
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · allenai/allenai/olmo-3-32b-think · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata allenai/Olmo-3-32B-Think@f2edda15216e738ef2bb73771e11890e152b2112 (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
42.6
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
42.6
Evidence status
confirmed · 77% mass
General preference
41.4
Coding
47.4
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
62%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
0.4
Liquidity (providers × uptime)
—
Open reach (HF downloads)
42.1
Surface (context / tools / modalities)
45.2
Freshness
37.3
  • · OpenRouter popularity #292
  • · HF 30d downloads 14248
  • · Catalogue: context 65536, reasoning
  • · First seen 2025-11-21

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
68.2
partial · 79% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
29.0
Evaluation provenance
47.3

Missing: deployability.independent-provider-records, deployability.measured-provider-uptime, deployability.published-provider-pricing, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
8.4
OpenRouter weekly popularity
#292 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#252 of 385
Rating
1305.5
95% confidence interval
1297–1314
Votes
6K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
0.4

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
42.1

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
37.3

Time since first public availability, on a six-month half-life.

Specification

Context window
66K tokens
Max output
66K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
Not offered
First seen on OpenRouter
21 Nov 2025

Capabilities

  • Supported: Reasoning
  • Not supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
f2edda15216e
Parameters
32.2B
Architecture
Olmo3ForCausalLM
Model type
olmo3
Hugging Face downloads (30d)
14K
Downloads (all time)
62K
Likes
174
Repository
allenai/Olmo-3-32B-Think
Repository updated
25 Jun 2026, 21:43 UTC
Base lineage
allenai/Olmo-3-32B-Think-DPO