Skip to main content

Model comparison

Kimi 3 vs Kimi K2.5

Data verified

Head-to-head evidence from 0 shared benchmark results across 0 categories. Overall scores shown here use BenchLM's provisional ranking lane.

Benchmark data for one or both models is coming soon. This page currently shows metadata and pricing where BenchLM has it, and score-level comparisons will populate as public benchmark results land.
Moonshot AI
N/A
No comparison
Moonshot AI
63/100
0 category wins0 category wins

Verified leaderboard positions: Kimi 3 unranked; Kimi K2.5 #23

Evidence parity. Kimi 3 and Kimi K2.5 share 0 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to Kimi 3; 65 to Kimi K2.5.

Updated July 14, 2026
Shared results
0
Kimi 3 only
0
Kimi K2.5 only
65
Comparable categories
0 / 8

Benchmark data for Kimi 3 and Kimi K2.5 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 0 shared benchmark results across 0 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM does not have sourced benchmark coverage for Kimi 3 yet. This comparison is currently limited to metadata such as context window, reasoning mode, and pricing where available.

Kimi K2.5 has the larger context window at 256K, compared with null for Kimi 3.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricKimi 3Kimi K2.5Comparison
Input / output priceUSD per 1M tokensKimi 3Not availableKimi K2.5$0.6 input / $3 outputA complete price comparison is not available.
Generation speedtokens per secondKimi 3Not availableKimi K2.545 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi 3Not availableKimi K2.52.38 sA complete latency comparison is not available.
Context windowmaximum listed tokensKimi 3Not availableKimi K2.5256KA complete context comparison is not available.

Benchmark Deep Dive

Agentic
BenchmarkKimi 3Kimi K2.5Result
Terminal-Bench 2.0Source 50.8%Not comparable
BrowseCompSource 60.6%Not comparable
Claw-EvalSource 52.3%Not comparable
QwenClawBenchSource 54.3%Not comparable
TAU3-BenchSource 65.7%Not comparable
DeepSearchQASource 77.1%Not comparable
DeepPlanningSource 14.4%Not comparable
ToolathlonSource 27.8%Not comparable
MCP AtlasSource 29.5%Not comparable
MCP-TasksSource 59.1%Not comparable
WideResearchSource 72.7%Not comparable
Tau2-TelecomSource 95.9%Not comparable
APEX-Agents-AASource 11.5%Not comparable
Gert LabsSource 45.88%Not comparable
ResearchClawBenchSource 14.0%Not comparable
JobBenchSource 8.7%Not comparable
AA Agentic IndexSource 21.7%Not comparable
GDPval-AASource 25.4%Not comparable
GDPval-AASource 1009Not comparable
Coding
BenchmarkKimi 3Kimi K2.5Result
SWE-bench VerifiedSource 76.8%Not comparable
SWE-bench Verified*Source 70.8%Not comparable
LiveCodeBenchSource 85%Not comparable
LiveCodeBench v6Source 85.0%Not comparable
SWE-bench ProSource 50.7%Not comparable
SWE MultilingualSource 73%Not comparable
SWE-RebenchSource 58.5%Not comparable
React Native EvalsSource 77.2%Not comparable
SciCodeSource 48.7%Not comparable
Terminal-Bench HardSource 34.8%Not comparable
AA-SciCodeSource 49.0%Not comparable
AA Coding IndexSource 46.8%Not comparable
Reasoning
BenchmarkKimi 3Kimi K2.5Result
LongBench v2Source 61%Not comparable
AA-LCRSource 65.3%Not comparable
CritPtSource 3.1%Not comparable
Knowledge
BenchmarkKimi 3Kimi K2.5Result
GPQASource 87.6%Not comparable
GPQA-DSource 87.6%Not comparable
SuperGPQASource 69.2%Not comparable
MMLU-ProSource 87.1%Not comparable
MMLU-Pro (Arcee)Source 87.1%Not comparable
HLESource 30.1%Not comparable
Artificial Analysis Intelligence IndexSource 35.4%Not comparable
AA-GPQA DiamondSource 87.9%Not comparable
AA-HLESource 29.4%Not comparable
AA-Omniscience IndexSource -8.1%Not comparable
AA-Omniscience AccuracySource 34.3%Not comparable
AA-Omniscience Hallucination RateSource 64.6%Not comparable
Math
BenchmarkKimi 3Kimi K2.5Result
AIME 2025Source 96.1%Not comparable
AIME26Source 95.8%Not comparable
AIME25 (Arcee)Source 96.3%Not comparable
HMMT Feb 2025Source 95.4%Not comparable
HMMT Nov 2025Source 91.1%Not comparable
HMMT Feb 2026Source 87.1%Not comparable
MMAnswerBenchSource 81.8%Not comparable
FrontierMath v2 (Tiers 1-3)Source 27.900%Not comparable
FrontierMath v2 (Tier 4)Source 4.200%Not comparable
Multilingual
BenchmarkKimi 3Kimi K2.5Result
MMLU-ProXSource 82.3%Not comparable
NOVA-63Source 56.0%Not comparable
Multimodal
BenchmarkKimi 3Kimi K2.5Result
MMMU-ProSource 78.5%Not comparable
Video-MMESource 87.4%Not comparable
MMVUSource 80.4%Not comparable
VideoMMMUSource 86.6%Not comparable
AA-MMMU-ProSource 75.4%Not comparable
Design Arena WebsiteSource 1284Not comparable
Inst. Following
BenchmarkKimi 3Kimi K2.5Result
IFEvalSource 93.9%Not comparable
AA-IFBenchSource 70.2%Not comparable
Frequently Asked Questions (3)

Can I compare Kimi 3 and Kimi K2.5 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Kimi 3 and Kimi K2.5 today?

Kimi 3: Pricing unavailable Kimi K2.5: $0.60 input / $3.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Self-host vs API cost

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

Kimi 3
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Model the full break-even

Related Comparisons

Last updated: July 14, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.