Benchmarks of K2 v213
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Documents1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
price not verifiedprice
—output speed?
512Kcontext
Rankingat medium effort?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow×2.4—$0.005Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking×5.1—$0.13Pass back reasoning_content+3BetterGPT-5.6 Lunalow×2.3—$0.01
BetterMistral Small 4thinkingOpen+25%—$0.015Context: 512K → 262KBetterMiMo v2.5thinkingOpen×2.4—$0.019ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×2.4—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.3—$0.01Mistral Small 4thinkingOpen+25%—$0.015Context: 512K → 262KMiMo v2.5thinkingOpen×2.4—$0.019
Granite 4.2 8BthinkingOpen+23%—$0.024Context: 512K → 128KModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×5.1—$0.13Pass back reasoning_content+3
DeepSeek V4.1 Flash 1017maxOpen×5—$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen×5—$2.01Reasoning cannot be disabled+3
Step 5 PreviewthinkingOpen×4.9—$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×4.8—$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
IK2 Horizon 375B A23BOpen×3.4—$1 / $4Training behavior may differ · Self-hosted trainingIK2 Horizon MoVA 36B A4BthinkingOpen×2.8—$1 / $4IK2 Horizon 7BthinkingOpen×2.3—$0.30 / $1.20IK2 Horizon 3.7BthinkingOpen+73%—$0.30 / $1.20IK2 Think V2Open+28%——Context: 512K → 262KIK2 Horizon 0.9BthinkingOpen-66%—$0.30 / $1.20Context: 512K → 131KAll Institute of Foundation Models models →Run it yourself
Fits onhardware needs not verified yet
LicenceApache-2.0free for commercial use
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam4.4#300
AA Omniscience Index-49#205
CritPt (physics)0#180
AA Omniscience · Accuracy17.9#186
GPQA Diamond59.8#228
AIME 2025 · AA archived64.7#76
Coding
LiveCodeBench · AA archived54.1#80
Agents & Tool Use
τ²-bench · AA24.9#174
Writing & Language
IFBench (instructions)55.1#101
FAQ
How much does K2 v2 cost?›
There is no per-unit API price: price not verified.
How good is K2 v2, and what is it best at?›
#297 of 334 in Chat & Knowledge, #131 of 239 in Coding, #172 of 242 in Agents & Tool Use, #101 of 245 in Writing & Language.
Is K2 v2 better than North Mini Code?›
On AA Intelligence Index 4.3.2, K2 v2 scores 9.9 vs 9.9 — about the same.
What is the context window of K2 v2?›
512K tokens.
When was K2 v2 released? Is there a newer version?›
Released 2025-12-05. It is the current version in its line.
Is K2 v2 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run K2 v2 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can K2 v2 read images?›
No, it accepts text only.
What is K2 v2?›
K2 v2 is an open-weights language model from Institute of Foundation Models, released Dec 2025.
What are the best alternatives to K2 v2?›
GPT-6 Luna (better), MiMo v2.6 Pro (open weights).