Benchmarks of Laguna M.17
BenchmarkByScoreRank
Coding3
Health & law4
No benchmark matches
—per task?
price not verifiedprice
—output speed?
262Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✗ 80 GB GPU
LicenceApache-2.0free for commercial use
Benchmarks
all categoriesChat & Knowledge
Vals LegalBench75.1#77
Vals MedCode23.1#76
Vals MedScribe65.9#74
Coding
WebDev Arena1,350#83
WebDev Arena · October 23, 20261,349.1#84
WebDev Arena · October 19, 20261,349.9#83
FAQ
How much does Laguna M.1 cost?›
There is no per-unit API price: price not verified.
How good is Laguna M.1, and what is it best at?›
#77 of 89 in Chat & Knowledge, #83 of 97 in Coding.
Is Laguna M.1 better than Llama 4 Scout?›
On Vals MedCode, Laguna M.1 scores 23.1 vs 23.3 — about the same.
What is the context window of Laguna M.1?›
262K tokens.
When was Laguna M.1 released? Is there a newer version?›
Released 2026-06-15. It is the current version in its line.
Is Laguna M.1 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Laguna M.1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Laguna M.1 read images?›
No, it accepts text only.
What is Laguna M.1?›
Laguna M.1 is an open-weights language model from poolside, released Jun 2026.
What are the best alternatives to Laguna M.1?›
Claude Haiku 4.5 (better), MiniMax M3 (open weights).