Olmo 3 7B Instruct
Nov 2025
Olmo 3 7B InstructCompare inon
Benchmarks of Olmo 3 7B Instruct12
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
price not verifiedprice
—output speed?
66Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow×4.1—$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×3.9—$0.30 / $1.20Memory (4-bit): 3.6 GB → 4.5 GB
BetterGranite 4.2 3BthinkingOpen+73%—$0.006
BetterGemma 4 E4BthinkingOpen+70%—$0.008Memory (4-bit): 3.6 GB → 4 GBBetterGPT-5.6 Lunalow×4—$0.01ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×4.1—$0.005Function calling only with none · Chat Completions+3Granite 4.2 3BthinkingOpen+73%—$0.006Gemma 4 E4BthinkingOpen+70%—$0.008Memory (4-bit): 3.6 GB → 4 GBGPT-5.6 Lunalow×4—$0.01GPT OSS 20BhighOpen+71%—$0.011Memory (4-bit): 3.6 GB → 13 GBModelScoreCostPer taskWhat changes
IK2 Horizon 7BthinkingOpen×3.9—$0.30 / $1.20Memory (4-bit): 3.6 GB → 4.5 GBIK2 Horizon 3.7BthinkingOpen×3—$0.30 / $1.20Gemma 4 12BthinkingOpen×2.7—$0.10 / $0.30Memory (4-bit): 3.6 GB → 6 GBSApriel v1.5 15B ThinkerOpen×2.6——Memory (4-bit): 3.6 GB → 7.4 GBSApriel v1.6 15B ThinkerOpen×2.6——Memory (4-bit): 3.6 GB → 7.4 GBModelScoreCostPer taskWhat changes
Olmo 3.1 32B ThinkthinkingOpen+36%——Memory (4-bit): 3.6 GB → 19 GBOlmo 3.1 32B Instructnon-thinkingOpen+24%—$0.20 / $0.60Memory (4-bit): 3.6 GB → 19 GBOlmo 3 32B ThinkthinkingOpen+24%——Memory (4-bit): 3.6 GB → 19 GBOlmo 3 7B ThinkOpensame——Molmo2 8Bnon-thinkingOpensame——Context: 66K → 37K+1All Allen Institute for AI models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam5.8#255
AA Omniscience Index-77.1#307
CritPt (physics)0#180
AA Intelligence Index 4.3.2≈5.2#313
AA Omniscience · Accuracy7.4#300
GPQA Diamond40#283
AIME 2025 · AA archived41.3#92
Coding
LiveCodeBench · AA archived26.6#129
Agents & Tool Use
τ²-bench · AA12.6#219
Writing & Language
IFBench (instructions)32.8#200
FAQ
How much does Olmo 3 7B Instruct cost?›
There is no per-unit API price: price not verified.
How good is Olmo 3 7B Instruct, and what is it best at?›
#253 of 334 in Chat & Knowledge, #210 of 239 in Coding, #216 of 242 in Agents & Tool Use, #198 of 245 in Writing & Language.
Is Olmo 3 7B Instruct better than Exaone 4.0 1.2B?›
On AA Intelligence Index 4.3.2, Olmo 3 7B Instruct scores 5.2 vs 5.3 — about the same.
What is the context window of Olmo 3 7B Instruct?›
66K tokens.
When was Olmo 3 7B Instruct released? Is there a newer version?›
Released 2025-11-20. It is the current version in its line.
Is Olmo 3 7B Instruct open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Olmo 3 7B Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Olmo 3 7B Instruct read images?›
No, it accepts text only.
What is Olmo 3 7B Instruct?›
Olmo 3 7B Instruct is an open-weights language model from Allen Institute for AI, released Nov 2025.
What are the best alternatives to Olmo 3 7B Instruct?›
GPT-6 Luna (better), K2 Horizon 7B (open weights).