Skip to main content

Model profile

Kimi K2.5 (Reasoning)

Moonshot AICurrentReleased Feb 1, 2026
Data verified
Overall Score
59.35Public #57 of 200
Arena Elo
1447
Eligible category ranks
2of 8
Price (1M tokens)
$0.6 in / $3 out
API pricing
Speed
Not listed
Context
128K

Evidence coverage

27 of 321 tracked benchmarks are published. 9 are verified and 18 provisional. 7 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
27 / 321
Verified
9
Provisional
18
Categories with evidence
7 / 8

Evidence by category

  • Agentic8 benchmarks
    Mixed evidence
  • Coding4 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge8 benchmarks
    Mixed evidence
  • Math1 benchmark
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal3 benchmarks
    Mixed evidence
  • Inst. Following1 benchmark
    Reported
ProprietarySelf-hostReasoning
Confidence:
Medium
reasoning

Kimi K2.5 (Reasoning) ranks #57 out of 200 models on the public leaderboard with an overall score of 59.35/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Kimi K2.5 (Reasoning) is a proprietary model with a 128K 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.

Kimi K2.5 (Reasoning) sits inside the Kimi K2.5 family alongside Kimi K2.5. This profile currently has 27 of 321 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 (#41), while its weakest is Agentic (#53). This performance profile makes it particularly well-suited for software development and code generation tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 59.059.72

  1. Qwen 3.6 Max (preview)
    Alibaba
    #5359.72
    Qwen 3.6 Max (preview) is #53 with a score of 59.72.
    Compare
  2. Kimi K2.5
    Moonshot AI
    #5459.66
    Kimi K2.5 is #54 with a score of 59.66.
    Compare
  3. MiniMax M2.5
    MiniMax
    #5559.52
    MiniMax M2.5 is #55 with a score of 59.52.
    Compare
  4. Qwen3.5 397B (Reasoning)
    Alibaba
    #5659.5
    Qwen3.5 397B (Reasoning) is #56 with a score of 59.5.
    Compare
  5. Kimi K2.5 (Reasoning)Current model
    Moonshot AI
    #5759.35
    Kimi K2.5 (Reasoning) is #57 with a score of 59.35.
  6. GPT-5.2-Codex
    OpenAI
    #5859.1
    GPT-5.2-Codex is #58 with a score of 59.1.
    Compare
  7. GPT-5.2 Instant
    OpenAI
    #5959.0
    GPT-5.2 Instant is #59 with a score of 59.0.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Coding67%
    Eligible cohort rank #41 of 122Category score 53.7
  2. Agentic56%
    Eligible cohort rank #53 of 119Category score 49.1

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #53 of 119Percentile 56thWeight 22%8 benchmarksMixed sources49.1
CodingRank #41 of 122Percentile 67thWeight 20%4 benchmarksMixed sources53.7
ReasoningRank Not rankedWeight 17%2 benchmarksReported70.0
KnowledgeRank Not rankedWeight 12%8 benchmarksMixed sources80.6
MathWeight 5%1 benchmarkVerifiedScore pending
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%3 benchmarksMixed sources65.9
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported94.0

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1447Not availableNot available

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic8 benchmarks
Terminal-Bench 2.0Provider exact
50.8%Weighted 38%
Source: MoonshotAI: Kimi K2.5Provenance: Provider exact
BrowseCompProvider exact
60.6%Weighted 28%
Source: MoonshotAI: Kimi K2.5 model cardProvenance: Provider exact
APEX-Agents-AAReported
11.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

95.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

32.58%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
AA Agentic IndexReported

Artificial Analysis Agentic Index

21.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

25.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported
1009Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding4 benchmarks
SWE-bench VerifiedProvider exact

Software Engineering Benchmark Verified

76.8%Weighted 16%
Source: MoonshotAI: Kimi K2.5Provenance: Provider exact
Vibe Code BenchBenchmark exact

Vibe Code Bench v1.1

17.54%Display only
Source: Vals AI: Vibe Code Bench v1.1Provenance: Vals Vibe Code Bench v1.1 reports this exact row under kimi/kimi-k2.5-thinking; BenchLM stores it on the local vibeCodeBench key.
AA-SciCodeReported

Artificial Analysis SciCode

49.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA Coding IndexReported

Artificial Analysis Coding Index

46.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

65.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

3.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge8 benchmarks
MMLU-ProProvider exact

Massive Multitask Language Understanding Professional

87.1%Weighted 30%
Source: MoonshotAI: Kimi K2.5 model cardProvenance: Provider exact
GPQAProvider exact

Graduate-Level Google-Proof Q&A

87.6%Weighted 7%
Source: MoonshotAI: Kimi K2.5 model cardProvenance: Provider exact
Artificial Analysis Intelligence IndexReported
35.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

87.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

29.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-8.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

34.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

64.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math1 benchmark
AIME 2025Provider exact

American Invitational Mathematics Examination 2025

96.1%Display only
Source: MoonshotAI: Kimi K2.5 model cardProvenance: Provider exact
Multimodal3 benchmarks
MMMU-ProProvider exact

Massive Multi-discipline Multimodal Understanding Pro

78.5%Weighted 45%
Source: MoonshotAI: Kimi K2.5 model cardProvenance: Provider exact
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

75.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Design Arena WebsiteReported

Design Arena Website Elo

1282Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

70.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Kimi K2.5 Family

Reasoning

Canonical Entry

Kimi K2.5

Frequently Asked Questions

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

Kimi K2.5 (Reasoning) has 27 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Kimi K2.5 (Reasoning) good for knowledge and understanding?

Kimi K2.5 (Reasoning) has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.5 (Reasoning) good for coding and programming?

Kimi K2.5 (Reasoning) ranks #41 out of 122 models in coding and programming benchmarks with an average score of 53.7. There are stronger options in this category.

Is Kimi K2.5 (Reasoning) good for mathematics?

Kimi K2.5 (Reasoning) has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.5 (Reasoning) good for reasoning and logic?

Kimi K2.5 (Reasoning) has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

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

Kimi K2.5 (Reasoning) ranks #53 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 49.1. There are stronger options in this category.

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

Kimi K2.5 (Reasoning) has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.5 (Reasoning) good for instruction following?

Kimi K2.5 (Reasoning) has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to Kimi K2.5 (Reasoning)?

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

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

Not yet. Kimi K2.5 (Reasoning) currently has 27 published benchmark scores out of the 321 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 (Reasoning)?

Kimi K2.5 (Reasoning) has a published context window of 128K, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.