Skip to main content
benchlm.ai

Kimi K2.5

Moonshot AISupersededReleased Feb 1, 2026
Overall Score
68Prov. #31 of 110Verified #9 of 14
Arena Elo
1400
Categories Ranked
8of 8
Price (1M tokens)
$0.5 in / $2.8 out
Speed
45tok/s
Context
256K
Open WeightNon-Reasoning
Confidence
base

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Kimi K2.5
API / mo$2,475
Self-host / mo$5,221
Break-even146M/day
Model the full break-even

According to BenchLM.ai, Kimi K2.5 ranks #31 out of 110 models on the provisional leaderboard with an overall score of 68/100. It also ranks #9 out of 14 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Kimi K2.5 is a open weight model with a 256K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

Kimi K2.5 sits inside the Kimi K2.5 family alongside Kimi K2.5 (Reasoning). This profile currently has 40 of 152 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 Coding (#12), while its weakest is Reasoning (#48). This performance profile makes it particularly well-suited for software development and code generation tasks.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#33
61.4/ 100
Weight: 22%11 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#12
81.6/ 100
Weight: 20%8 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#48
55.4/ 100
Weight: 17%1 benchmark
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#31
70.3/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#45
57.3/ 100
Weight: 5%7 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#30
70.7/ 100
Weight: 7%2 benchmarks
MGSMMMLU-ProX

Multimodal

#46
64.5/ 100
Weight: 12%4 benchmarks
MMMU-ProOfficeQA Pro

Inst. Following

#28
82.0/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1400

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 K2.5 Family

Base entry

Kimi K2.5 (Reasoning)Prov. 79

Compare This Model

See how Kimi K2.5 stacks up against similar models

Kimi K2.5 (Reasoning)Moonshot AI
Prov. 79
Kimi 2.6Moonshot AI
Prov. 83
Kimi K2Moonshot AI
Prov. 43
Moonshot v1Moonshot AI
Prov. 24
Claude Mythos PreviewAnthropic
Prov. 99

Frequently Asked Questions

How does Kimi K2.5 perform overall in AI benchmarks?

Kimi K2.5 currently ranks #31 out of 110 models on BenchLM's provisional leaderboard with an overall score of 68. It also ranks #9 out of 14 on the verified leaderboard. It is created by Moonshot AI and features a 256K context window.

Is Kimi K2.5 good for knowledge and understanding?

Kimi K2.5 ranks #31 out of 110 models in knowledge and understanding benchmarks with an average score of 70.3. There are stronger options in this category.

Is Kimi K2.5 good for coding and programming?

Kimi K2.5 ranks #12 out of 110 models in coding and programming benchmarks with an average score of 81.6. There are stronger options in this category.

Is Kimi K2.5 good for mathematics?

Kimi K2.5 ranks #45 out of 110 models in mathematics benchmarks with an average score of 57.3. There are stronger options in this category.

Is Kimi K2.5 good for reasoning and logic?

Kimi K2.5 ranks #48 out of 110 models in reasoning and logic benchmarks with an average score of 55.4. There are stronger options in this category.

Is Kimi K2.5 good for agentic tool use and computer tasks?

Kimi K2.5 ranks #33 out of 110 models in agentic tool use and computer tasks benchmarks with an average score of 61.4. There are stronger options in this category.

Is Kimi K2.5 good for multimodal and grounded tasks?

Kimi K2.5 ranks #46 out of 110 models in multimodal and grounded tasks benchmarks with an average score of 64.5. There are stronger options in this category.

Is Kimi K2.5 good for instruction following?

Kimi K2.5 ranks #28 out of 110 models in instruction following benchmarks with an average score of 82. There are stronger options in this category.

Is Kimi K2.5 good for multilingual tasks?

Kimi K2.5 ranks #30 out of 110 models in multilingual tasks benchmarks with an average score of 70.7. There are stronger options in this category.

Is Kimi K2.5 open source?

Yes, Kimi K2.5 is an open weight model created by Moonshot AI, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Which sibling models are related to Kimi K2.5?

Kimi K2.5 belongs to the Kimi K2.5 family. Related variants on BenchLM include Kimi K2.5 (Reasoning).

Does Kimi K2.5 have full benchmark coverage on BenchLM?

Not yet. Kimi K2.5 currently has 40 published benchmark scores out of the 152 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 K2.5?

Kimi K2.5 has a context window of 256K, which determines how much text it can process in a single interaction.

Related Resources

More from Moonshot AI LLM Pricing Comparison BenchLM Methodology The AI Race Which LLM Should I Use? Benchmark Explainers
Last updated: April 20, 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.