AllenAI: Olmo 3 32B Think
allenai/olmo-3-32b-think
174th smartest of 182ReasoningJSON
Intelligence
6.4
174th of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.150
84th cheapest
Context
66K
66K max out
How it compares
Smarter than4%
of all ranked models
Cheaper than75%
of all ranked models
Overview
Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis20th percentile
Intelligence Index
6.4
GPQA Diamond
61%
Humanity's Last Exam
6%
SciCode
29%
Tau²-Bench (agentic)
0%
Specifications
Context window66K
Max output66K
Knowledge cutoff—
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsallenai/Olmo-3-32B-Think ↗
Olmo 3 32B Think FAQ
How much does Olmo 3 32B Think cost?
Olmo 3 32B Think costs $0.150 per million input tokens and $0.500 per million output tokens via OpenRouter, making it 84th cheapest of 332 paid models.
How smart is Olmo 3 32B Think?
Olmo 3 32B Think scores 6.4 on the Artificial Analysis Intelligence Index, ranking 174th of 182 benchmarked models, with a GPQA Diamond score of 61%.
What is Olmo 3 32B Think's context window?
Olmo 3 32B Think supports a 66K-token context window and can output up to 66K tokens. It accepts text input.
Similar models
All Olmo 3 32B Think alternatives →Compare head-to-head
AllenAI: Olmo 3 32B Think vs Mistral: SabaAllenAI: Olmo 3 32B Think vs IBM: Granite 4.1 8BAllenAI: Olmo 3 32B Think vs Google: Gemini 2.5 Flash LiteAllenAI: Olmo 3 32B Think vs Google: Gemini 2.5 Flash Lite (batch)AllenAI: Olmo 3 32B Think vs OpenAI: GPT-4o-miniAllenAI: Olmo 3 32B Think vs OpenAI: GPT-4o-mini (2024-07-18)