Benchmarks of MiniCPM5 2B16
BenchmarkByScoreRank
Overall1
Knowledge3
Science3
Coding2
Agents4
Documents2
Legacy · saturated or no longer reported1
No benchmark matches
—per task?
price not verifiedprice
—output speed?
131Kcontext
Rankingin thinking mode?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow+78%—$0.005Function calling only with none · Chat Completions+3
OpenGranite 4.2 8Bthinking+20%—$0.024Context: 131K → 128K+1BetterGPT-5.6 Lunalow+75%—$0.01BetterGPT OSS 20BhighOpen+48%—$0.011Memory (4-bit): 1.3 GB → 13 GB
BetterMistral Small 4thinkingOpen+48%—$0.015Memory (4-bit): 1.3 GB → 72 GBModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow+78%—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+75%—$0.01GPT OSS 20BhighOpen+48%—$0.011Memory (4-bit): 1.3 GB → 13 GBMistral Small 4thinkingOpen+48%—$0.015Memory (4-bit): 1.3 GB → 72 GB
Nemotron 3 Nano 30B A3BthinkingOpen+16%—$0.017Memory (4-bit): 1.3 GB → 19 GBModelScoreCostPer taskWhat changes
Granite 4.2 8BthinkingOpen+20%—$0.024Context: 131K → 128K+1
Qwen 3.5 9BthinkingOpen+12%—$0.21Memory (4-bit): 1.3 GB → 4.8 GBQwen3 8BthinkingOpen+6%—$0.18 / $0.70Context: 131K → 33K+1IK2 Horizon 7BthinkingOpen+5%—$0.30 / $1.20Memory (4-bit): 1.3 GB → 4.5 GBGranite 4.2 3BthinkingOpensame—$0.006Context: 131K → 128K+1Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 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 Exam8.9#204
AA Omniscience Index-11.7#102
CritPt (physics)0.3#149
AA Intelligence Index 4.3.212.5#177
AA Omniscience · Accuracy8.4#294
AA-LCR (long context) 1.159.3#161
GDP.pdf · AA all-pass1.4#112
GPQA Diamond70.2#183
Coding
SciCode26.3#127
Terminal-Bench 2.18.6#129
Agents & Tool Use
AutomationBench-AA1.8#101
GDPval-AA (work tasks) 2.110.4#111
τ³-Banking · AA20.8#53
AA-Briefcase 1.1 · Elo423#101
FAQ
How much does MiniCPM5 2B cost?›
There is no per-unit API price: price not verified.
How good is MiniCPM5 2B, and what is it best at?›
#203 of 334 in Chat & Knowledge, #75 of 132 in Coding, #101 of 133 in Agents & Tool Use, #112 of 133 in Vision & Documents.
Is MiniCPM5 2B better than K2 Horizon 7B?›
On SciCode, MiniCPM5 2B scores 26.3 vs 27.5 — lower.
What is the context window of MiniCPM5 2B?›
131K tokens.
When was MiniCPM5 2B released? Is there a newer version?›
Released 2026-09-07. It is the current version in its line.
Is MiniCPM5 2B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run MiniCPM5 2B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can MiniCPM5 2B read images?›
No, it accepts text only.
What is MiniCPM5 2B?›
MiniCPM5 2B is an open-weights language model from OpenBMB, released Sep 2026.
What are the best alternatives to MiniCPM5 2B?›
GPT-6 Luna (better), Granite 4.2 8B (open weights).