Skip to main content
BenchLM
Advertise

Model comparison

Kimi K2 vs Kimi K2.5

Data verified

Head-to-head evidence from 14 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Kimi K2
Moonshot AI
27.19/100
Margin
32.5pts
winning →
Kimi K2.5
Moonshot AI
59.66/100
0 category wins1 category wins

Public leaderboard positions: Kimi K2 #189 (Supported); Kimi K2.5 #54 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K2 and Kimi K2.5 share 14 comparable benchmark results. 1 of 8 categories are comparable. 0 results are unique to Kimi K2; 49 to Kimi K2.5.

Updated July 22, 2026
Shared results
14
Kimi K2 only
0
Kimi K2.5 only
49
Comparable categories
1 / 8

Pick Kimi K2.5 if you want the stronger benchmark profile. Kimi K2 only becomes the better choice if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 7 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Kimi K2.5 is clearly ahead on the BenchAlign aggregate, 59.66 to 27.19. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K2.5's sharpest advantage is in mathematics, where it averages 60.6 against 16.1. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 21.404% to 27.900%.

Kimi K2.5 is also the more expensive model on tokens at $0.60 input / $3.00 output per 1M tokens, versus $0.60 input / $2.50 output per 1M tokens for Kimi K2. Kimi K2.5 gives you the larger context window at 256K, compared with 128K for Kimi K2.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Kimi K2 and Kimi K2.5
CategoryKimi K2ΔKimi K2.5
MathKimi K216.1Margin→ 44.5Kimi K2.560.6
AgenticKimi K2Not measuredMarginNo overlapKimi K2.555.0
CodingKimi K2Not measuredMarginNo overlapKimi K2.559.4
ReasoningKimi K2Not measuredMarginNo overlapKimi K2.561.0
KnowledgeKimi K2Not measuredMarginNo overlapKimi K2.556.9
MultilingualKimi K2Not measuredMarginNo overlapKimi K2.582.3
MultimodalKimi K2Not measuredMarginNo overlapKimi K2.578.5
Inst. FollowingKimi K2Not measuredMarginNo overlapKimi K2.593.9

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Kimi K2B · Kimi K2.5

  1. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 21.404%B 27.900%
    Winner: Kimi K2.5Δ 6.5
    FrontierMath v2 (Tiers 1-3): Kimi K2 scored 21.404%; Kimi K2.5 scored 27.900%. Kimi K2.5 wins this benchmark.

  2. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 0.000%B 4.200%
    Winner: Kimi K2.5Δ 4.2
    FrontierMath v2 (Tier 4): Kimi K2 scored 0.000%; Kimi K2.5 scored 4.200%. Kimi K2.5 wins this benchmark.

Operational comparison

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

MetricKimi K2Kimi K2.5Comparison
Input / output priceUSD per 1M tokensKimi K2$0.6 input / $2.5 outputKimi K2.5$0.6 input / $3 outputKimi K2 has the lower combined listed price.
Generation speedtokens per secondKimi K243 tok/sKimi K2.545 tok/sKimi K2.5 has the higher measured throughput.
First-answer latencyseconds to first tokenKimi K21.51 sKimi K2.52.38 sKimi K2 reaches the first token sooner.
Context windowmaximum listed tokensKimi K2128KKimi K2.5256KKimi K2.5 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkKimi K2Kimi K2.5Result
τ²-bench resultsSource 61.1%95.9%Kimi K2.5 leads
Terminal-Bench 2.0Source —50.8%Not comparable
BrowseCompSource —60.6%Not comparable
Claw-EvalSource —52.3%Not comparable
QwenClawBenchSource —54.3%Not comparable
τ³-bench resultsSource —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
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 K2Kimi K2.5Result
AA-SciCodeSource 34.5%49.0%Kimi K2.5 leads
SWE-bench VerifiedSource —76.8%Not comparable
SWE-bench Verified*Source —70.8%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
AA Coding IndexSource —46.8%Not comparable
Reasoning
BenchmarkKimi K2Kimi K2.5Result
AA-LCRSource 51.0%65.3%Kimi K2.5 leads
CritPtSource 0.0%3.1%Kimi K2.5 leads
LongBench v2Source —61%Not comparable
Knowledge
BenchmarkKimi K2Kimi K2.5Result
Artificial Analysis Intelligence IndexSource 19.4%35.4%Kimi K2.5 leads
AA-GPQA DiamondSource 76.6%87.9%Kimi K2.5 leads
AA-HLESource 7.0%29.4%Kimi K2.5 leads
AA-Omniscience IndexSource -27.5%-8.1%Kimi K2.5 leads
AA-Omniscience AccuracySource 26.8%34.3%Kimi K2.5 leads
AA-Omniscience Hallucination RateSource 74.2%64.6%Kimi K2.5 leads
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
MathKimi K2.5 wins
BenchmarkKimi K2Kimi K2.5Result
FrontierMath v2 (Tiers 1-3)Source 21.404%27.900%Kimi K2.5 leads
FrontierMath v2 (Tier 4)Source 0.000%4.200%Kimi K2.5 leads
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
Multilingual
BenchmarkKimi K2Kimi K2.5Result
MMLU-ProXSource —82.3%Not comparable
NOVA-63Source —56.0%Not comparable
Multimodal
BenchmarkKimi K2Kimi K2.5Result
Design Arena WebsiteSource 10801279Kimi K2.5 leads
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
Inst. Following
BenchmarkKimi K2Kimi K2.5Result
AA-IFBenchSource 41.5%70.2%Kimi K2.5 leads
IFEvalSource —93.9%Not comparable
Frequently Asked Questions (2)

Which is better, Kimi K2 or Kimi K2.5?

Kimi K2.5 is ahead on BenchLM's BenchAlign leaderboard, 59.66 to 27.19. The biggest single separator in this matchup is FrontierMath v2 (Tiers 1-3), where the scores are 21.404% and 27.900%.

Which is better for math, Kimi K2 or Kimi K2.5?

Kimi K2.5 has the edge for math in this comparison, averaging 60.6 versus 16.1. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.

Self-host vs API cost

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

Kimi K2
API / mo$2,325
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

Explore More

Moonshot AI Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 22, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.