Ai2: Olmo 3 7B Think
Model Type
Open Weight Model
7B parameters
Recommended Use Cases
Text Generation
Try Olmo 3 7B Think
The Think model from the OLMo 3 model family — a fully open 7B parameter reasoning model from Ai2 (Allen Institute for AI). Unlike other open LLMs, OLMo provides complete access to training data, code, checkpoints, and logs.
Per its creators, Ai2:
OLMo 3 7B Think delivers strong reasoning capabilities at 7B scale, surfacing intermediate thinking steps for complex prompts at high efficiency.
Long chain-of-thought thinking improves reasoning tasks like math and coding.
Key Capabilities
- Math: 95.1% on MATH, 71.6% on AIME 2024, 64.6% on AIME 2025
- Coding: 89.9% on HumanEvalPlus, 75.2% on LiveCodeBench v3
- Reasoning: 86.6% on BigBenchHard, 66.5% on ZebraLogic