Ling Mini 2.0
Sep 2025
Ling Mini 2.0Compare inon
Benchmarks of Ling Mini 2.012
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
self-host onlyprice
—output speed?
32Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow+14%—$0.005Function calling only with none · Chat Completions+3OOpenMiniCPM5 1Bnon-thinking×106.4——
BetterGranite 4.2 3BthinkingOpen×3.6—$0.006
BetterMinistral 3 3B 2512Open+20%—$0.008
BetterGemma 4 E4BthinkingOpen×3.1—$0.008ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow+14%—$0.005Function calling only with none · Chat Completions+3Granite 4.2 3BthinkingOpen×3.6—$0.006Ministral 3 3B 2512Open+20%—$0.008Gemma 4 E4BthinkingOpen×3.1—$0.008GPT-5.6 Lunalow+7%—$0.01ModelScoreCostPer taskWhat changes
OMiniCPM5 1Bnon-thinkingOpen×106.4——AG9v3 3BOpen×8.2——AG9v3 39A5BOpen×7.4——Memory (4-bit): 9.8 GB → 23 GBlLFM2.5 2.6BthinkingOpen×6——
Qwen3.8 27Bnon-thinkingOpen×5.3—$2.49Memory (4-bit): 9.8 GB → 17 GB+5ModelScoreCostPer taskWhat changes
Ling 2.6 FlashOpensame——Memory (4-bit): 9.8 GB → 64 GBLing 1Tnon-thinkingOpen+1%—$0.57 / $2.29Memory (4-bit): 9.8 GB → 600 GBLing 2.6 1TOpen+3%——Memory (4-bit): 9.8 GB → 615 GBRing Flash 2.0thinkingOpen+6%——Memory (4-bit): 9.8 GB → 62 GBRing 1TOpen+7%—$0.57 / $2.29Memory (4-bit): 9.8 GB → 600 GBLing Flash 2.0non-thinkingOpen+7%—$0.14 / $0.57Memory (4-bit): 9.8 GB → 62 GBRing 2.6 1TOpen+12%—$0.29Memory (4-bit): 9.8 GB → 615 GBLing 3.0 FlashthinkingOpen×2.2—$0.06 / $0.18Memory (4-bit): 9.8 GB → 76 GBAll inclusionAI models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✓ 16 GB · compressed✓ 24 GB GPU · 8-bit✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam5.1#271
AA Omniscience Index-78.5#311
CritPt (physics)0#180
AA Intelligence Index 4.3.2≈5.5#309
AA Omniscience · Accuracy8.9#289
GPQA Diamond56.2#243
AIME 2025 · AA archived49.3#90
Coding
LiveCodeBench · AA archived42.9#100
Agents & Tool Use
τ²-bench · AA13.2#216
Writing & Language
IFBench (instructions)23.6#235
FAQ
How much does Ling Mini 2.0 cost?›
There is no per-unit API price: self-host only.
Is Ling Mini 2.0 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Ling Mini 2.0, and what is it best at?›
#269 of 334 in Chat & Knowledge, #203 of 239 in Coding, #213 of 242 in Agents & Tool Use, #232 of 245 in Writing & Language.
Is Ling Mini 2.0 better than Granite 4.0 Micro?›
On AA Omniscience · Hallucination Rate, Ling Mini 2.0 scores 95.9 vs 95.8 — about the same.
What is the context window of Ling Mini 2.0?›
32K tokens.
When was Ling Mini 2.0 released? Is there a newer version?›
Released 2025-09-09. It has been superseded by Ling 3.0 Tiny.
Is Ling Mini 2.0 open source?›
Yes, the weights are open (MIT licence).
Can I run Ling Mini 2.0 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Ling Mini 2.0 read images?›
No, it accepts text only.
What is Ling Mini 2.0?›
Ling Mini 2.0 is an open-weights language model from inclusionAI, released Sep 2025.
What are the best alternatives to Ling Mini 2.0?›
GPT-6 Luna (better), MiniCPM5 1B (open weights).