AllenAI: Olmo 3.1 32B Think
Analysis Summary
AllenAI Olmo 3.1 32B Think is a reasoning-focused open model from the Allen Institute for AI, featuring a dedicated thinking mode that drives strong performance on math and instruction-following benchmarks. Its MMLU Pro and AIME scores are well above its intelligence index peers, suggesting the reasoning mode adds real value for structured problem-solving tasks.
For businesses, it suits analytical workloads where step-by-step reasoning matters: financial modelling support, structured Q&A, or document analysis within its 65K context limit. Coding capability is limited, and the absence of tool use or function calling reduces its fit for agentic pipelines. No vision support further narrows its scope.
At $0.15 input and $0.50 output, pricing is mid-range for this capability tier. Teams needing a capable reasoning model for text-only analytical tasks on a moderate budget will find it useful, but those requiring coding, agents, or multimodal input should look elsewhere.
Assessed June 17, 2026
Editorial notes
AllenAI Olmo 3.1 32B Think delivers strong math and instruction-following benchmarks with a notable reasoning mode, but limited coding scores and a 65K context window cap its business versatility.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How AllenAI: Olmo 3.1 32B Think compares
AllenAI: Olmo 3.1 32B Think ranks #261 of 380 AI models we track for overall intelligence. Its 66K-token context window is larger than 34% of the models we list. At $0.15 per million input tokens it is cheaper than 57% of comparable models.
About AllenAI: Olmo 3.1 32B Think
Olmo 3.1 32B Think is a large-scale, 32-billion-parameter model designed for deep reasoning, complex multi-step logic, and advanced instruction following. Building on the Olmo 3 series, version 3.1 delivers refined reasoning behavior and stronger performance across demanding evaluations and nuanced conversational tasks. Developed by Ai2 under the Apache 2.0 license, Olmo 3.1 32B Think continues the Olmo initiativeās commitment to openness, providing full transparency across model weights, code, and training methodology.
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does AllenAI: Olmo 3.1 32B Think stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
allenai/olmo-3.1-32b-think
|
| Provider | allenai |
| Release Date | December 16, 2025 |
| Context Length | 65,536 tokens |
| Max Completion | 65,536 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.15 | $0.000150 |
| Output | $0.50 | $0.000500 |
Leaderboard Categories
External Resources
Frequently asked questions about AllenAI: Olmo 3.1 32B Think
How much does AllenAI: Olmo 3.1 32B Think cost?
AllenAI: Olmo 3.1 32B Think costs $0.15 per million input tokens and $0.50 per million output tokens.
What is the context window of AllenAI: Olmo 3.1 32B Think?
AllenAI: Olmo 3.1 32B Think has a context window of 65,536 tokens (66K).
Who created AllenAI: Olmo 3.1 32B Think?
AllenAI: Olmo 3.1 32B Think is developed by AllenAI and was released on December 16, 2025.
