Benchmarks of Olmo 3.1 32B Think26
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Writing14
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
self-host onlyprice
—output speed?
66Kcontext
Rankingin thinking mode?
Alternatives?
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
History
2 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam6.3#242
AA Omniscience Index-43.4#184
CritPt (physics)0#180
AA Intelligence Index 4.3.2≈7.1#276
AA Omniscience · Accuracy13.8#253
GPQA Diamond59.1#230
AIME 2025 · AA archived77.3#52
Coding
LiveCodeBench · AA archived69.5#46
Agents & Tool Use
τ²-bench · AA0#232
Writing & Language
FAQ
How much does Olmo 3.1 32B Think cost?›
There is no per-unit API price: self-host only.
Is Olmo 3.1 32B Think free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Olmo 3.1 32B Think, and what is it best at?›
#240 of 334 in Chat & Knowledge, #210 of 239 in Coding, #229 of 242 in Agents & Tool Use, #160 of 195 in Writing & Language.
Is Olmo 3.1 32B Think better than Olmo 3 32B Think?›
On LiveCodeBench · AA archived, Olmo 3.1 32B Think scores 69.5 vs 67.2 — higher.
What is the context window of Olmo 3.1 32B Think?›
66K tokens.
When was Olmo 3.1 32B Think released? Is there a newer version?›
Released 2025-12-12. It is the current version in its line.
Is Olmo 3.1 32B Think open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Olmo 3.1 32B Think locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Olmo 3.1 32B Think read images?›
No, it accepts text only.
What is Olmo 3.1 32B Think?›
Olmo 3.1 32B Think is an open-weights language model from Allen Institute for AI, released Dec 2025, the successor to Olmo 3 32B Think.
What are the best alternatives to Olmo 3.1 32B Think?›
GPT OSS 20B (better), Apriel v1.6 15B Thinker (open weights).