Skip to main content

Kimi K2.6

Moonshot AICurrentReleased Apr 20, 2026
Overall Score
84Prov. #12 of 115Verified #6 of 23
Arena Elo
1459
Categories Ranked
3of 8
Price (1M tokens)
$0.95 in / $4 out
Speed
N/A
Context
256K
Open WeightSelf-hostReasoning
Confidence
base

According to BenchLM.ai, Kimi K2.6 ranks #12 out of 115 models on the provisional leaderboard with an overall score of 84/100. It also ranks #6 out of 23 on the verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.

Kimi K2.6 is a open weight model with a 256K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

BenchLM links it directly to Kimi K2.5 as the earlier related model in that lineage. This profile currently has 27 of 178 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Agentic (#7), while its weakest is Multimodal & Grounded (#26). This performance profile makes it particularly useful for coding agents, browser research, and computer-use workflows.

Ranking Distribution

Category rank across 4 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#7
87.9/ 100
Weight: 22%8 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#7
88.7/ 100
Weight: 20%8 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

0.0/ 100
Weight: 17%0 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

75.8/ 100
Weight: 12%3 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

0.0/ 100
Weight: 5%3 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

0.0/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#26
68.1/ 100
Weight: 12%5 benchmarks
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

0.0/ 100
Weight: 5%0 benchmarks
IFEvalIFBench

Chatbot Arena Performance

Text Overall1459CI: ±8.14,901 votes
Coding1514CI: ±16.51,162 votes
Math1460CI: ±32.1276 votes
Instruction Following1458CI: ±14.71,447 votes
Creative Writing1422CI: ±21.9676 votes
Multi-turn1458CI: ±20.5757 votes
Hard Prompts1484CI: ±10.42,880 votes
Hard Prompts (English)1484CI: ±15.61,308 votes
Longer Query1467CI: ±14.41,505 votes

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Kimi K2.6 Family

Base entry

Related Earlier Model

Kimi K2.5

Frequently Asked Questions

How does Kimi K2.6 perform overall in AI benchmarks?

Kimi K2.6 currently ranks #12 out of 115 models on BenchLM's provisional leaderboard with an overall score of 84. It also ranks #6 out of 23 on the verified leaderboard. It is created by Moonshot AI and features a 256K context window.

Is Kimi K2.6 good for knowledge and understanding?

Kimi K2.6 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.6 good for coding and programming?

Kimi K2.6 ranks #7 out of 115 models in coding and programming benchmarks with an average score of 88.7. It is among the top performers in this category.

Is Kimi K2.6 good for mathematics?

Kimi K2.6 has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.6 good for agentic tool use and computer tasks?

Kimi K2.6 ranks #7 out of 115 models in agentic tool use and computer tasks benchmarks with an average score of 87.9. It is among the top performers in this category.

Is Kimi K2.6 good for multimodal and grounded tasks?

Kimi K2.6 ranks #26 out of 115 models in multimodal and grounded tasks benchmarks with an average score of 68.1. There are stronger options in this category.

Is Kimi K2.6 open source?

Yes, Kimi K2.6 is an open weight model created by Moonshot AI, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does Kimi K2.6 have full benchmark coverage on BenchLM?

Not yet. Kimi K2.6 currently has 27 published benchmark scores out of the 178 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Kimi K2.6?

Kimi K2.6 has a context window of 256K, which determines how much text it can process in a single interaction.

Last updated: April 29, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.