North Mini Code
Jun 2026
North Mini CodeCompare inon
North Mini Code measured on 9 of 42 Agents & Tool Use benchmarks9
BenchmarkByScoreRank
Agents7
Documents1
Legacy · saturated or no longer reported1
No benchmark matches
—per task?
free API onlyprice
66 tok/sfirst token in 0.5 s?
256Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterMiMo v2.5thinkingOpen+34%—$0.042Memory (4-bit): 18 GB → 186 GB
OpenGemma 4 31Bthinking+17%—$0.10 / $0.34Memory (4-bit): 18 GB → 19 GB
BetterGPT-5 Minihigh+7%—$0.053
BetterMiniMax M2.7thinkingOpen+27%—$0.11Context: 256K → 205K+1BetterGPT-5.6 Terralow+41%—$0.14Prompts with >272K input tokensModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
MiMo v2.5thinkingOpen+34%—$0.042Memory (4-bit): 18 GB → 186 GBGPT-5 Minihigh+7%—$0.053MiniMax M2.7thinkingOpen+27%—$0.11Context: 256K → 205K+1GPT-5.6 Terralow+41%—$0.14Prompts with >272K input tokensMiMo v2.5 ProthinkingOpen+39%—$0.15Memory (4-bit): 18 GB → 614 GBModelScoreCostPer taskWhat changes
Gemma 4 31BthinkingOpen+17%—$0.10 / $0.34Memory (4-bit): 18 GB → 19 GB
Qwen3.6 27BthinkingOpen+12%—$0.62Qwen3.6 35B A3BthinkingOpen+12%—$0.48Memory (4-bit): 18 GB → 22 GBQwen 3.5 27BthinkingOpen+5%—$0.30 / $2.40Qwen 3.5 35B A3BthinkingOpen-15%—$0.25 / $2Memory (4-bit): 18 GB → 22 GBModelScoreCostPer taskWhat changes
Command A+thinkingOpen-20%—$0.30 / $1.50Context: 256K → 128K+1Command Anon-thinkingOpen-98%—$2.50 / $10Memory (4-bit): 18 GB → 67 GBTiny Aya GlobalOpen-100%——Context: 256K → 8K+1Command R7B (12-2024)Openn/a—$0.037 / $0.15Context: 256K → 128K+1Command R (08-2024)unstatedOpenn/a—$0.15 / $0.60Context: 256K → 128K+1Command R+ (08-2024)unstatedOpenn/a—$2.50 / $10Context: 256K → 128K+1Command R+Openn/a——Context: 256K → 128K+1Command ROpenn/a——Context: 256K → 128K+1All Cohere models →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
Benchmarks
in Agents & Tool UseTerminal-Bench 2.135.6#91
Terminal-Bench 4.00.5#65
GDPval-AA (work tasks) 2.1310.7#114
AA-LCR (long context) 1.137.3#208
τ²-bench · AA37.4#131
τ³-Banking · AA6.4#107
AutomationBench-AA1.5#107
AA-Briefcase 1.1 · Elo211.7#118
FAQ
How much does North Mini Code cost?›
There is no per-unit API price: free API only.
Is North Mini Code free to use?›
Yes, there is a free API option.
How good is North Mini Code, and what is it best at?›
#174 of 336 in Chat & Knowledge, #65 of 134 in Coding, #107 of 135 in Agents & Tool Use, #93 of 245 in Writing & Language, #109 of 135 in Vision & Documents.
Is North Mini Code better than GLM 4.7?›
On Terminal-Bench Hard (version unstated), North Mini Code scores 31.1 vs 31.8 — about the same.
What is the context window of North Mini Code?›
256K tokens, with up to 64K output tokens.
When was North Mini Code released? Is there a newer version?›
Released 2026-06-09. It is the current version in its line.
Is North Mini Code open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run North Mini Code locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can North Mini Code read images?›
No, it accepts text only.
What is North Mini Code?›
North Mini Code is an open-weights language model from Cohere, released Jun 2026.
What are the best alternatives to North Mini Code?›
MiMo v2.5 (better), Gemma 4 31B (open weights).