Olmo 3.1 32B Instruct benchmarks, price, and specs | Tokens or Towers

AA Intelligence: 6.5#126 of 142
Price: Self-host
Output speed: —
Context window: 66K tokens

Composite indexes

Artificial Analysis Intelligence Index#126 of 142
7independentIntelligence Index v4.3; non-reasoning; estimatedArtificial Analysis: Olmo 3.1 32B Instruct ↗
Leader: Claude Opus 5.5 at 58

Agents and tool use

τ²-Bench#65 of 88
21.3%independenttelecom; non-reasoningArtificial Analysis: Olmo 3.1 32B Instruct ↗
Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

GPQA Diamond#120 of 142
53.9%independentnon-reasoningArtificial Analysis: Olmo 3.1 32B Instruct ↗
Leader: GPT-6 Astra at 96.1%
Humanity’s Last Exam#122 of 147
5%independentno tools; non-reasoningArtificial Analysis: Olmo 3.1 32B Instruct ↗
Leader: Claude Opus 5.5 at 61.4%
CritPt#125 of 139
0%independentnon-reasoningArtificial Analysis: Olmo 3.1 32B Instruct ↗
Leader: GPT-5.6 Sol at 32.3%

Vision and long context

AA Long Context Reasoning#132 of 139
0%independentnon-reasoningArtificial Analysis: Olmo 3.1 32B Instruct ↗
Leader: Kimi K3 at 88.7%

Other published results

Result	Score	Reported by	Source
Terminal-Bench Hard (AA) · non-reasoning	0%	independent	Artificial Analysis: Olmo 3.1 32B Instruct ↗
IFBench · non-reasoning	39.2%	independent	Artificial Analysis: Olmo 3.1 32B Instruct ↗
AA-Omniscience Index · non-reasoning	-52.4 index	independent	Artificial Analysis: Olmo 3.1 32B Instruct ↗