Skip to main content
BenchLM
Advertise

Model comparison

Claude Haiku 4.5 vs Kimi K2.5

Data verified

Head-to-head evidence from 5 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.58/100
Margin
3.1pts
winning →
Kimi K2.5
Moonshot AI
59.66/100
1 category wins1 category wins

Public leaderboard positions: Claude Haiku 4.5 #77 (Estimated); Kimi K2.5 #54 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Haiku 4.5 and Kimi K2.5 share 5 comparable benchmark results. 2 of 8 categories are comparable. 0 results are unique to Claude Haiku 4.5; 58 to Kimi K2.5.

Updated July 22, 2026
Shared results
5
Claude Haiku 4.5 only
0
Kimi K2.5 only
58
Comparable categories
2 / 8

Pick Kimi K2.5 if you want the stronger benchmark profile. Claude Haiku 4.5 only becomes the better choice if coding is the priority.

Confidence note. This is a partial-evidence comparison with 5 shared benchmark results across 4 evidence categories; 2 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 56.58. 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 4.9. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 5.903% to 27.900%. Claude Haiku 4.5 does hit back in coding, so the answer changes if that is the part of the workload you care about most.

Claude Haiku 4.5 is also the more expensive model on tokens at $1.00 input / $5.00 output per 1M tokens, versus $0.60 input / $3.00 output per 1M tokens for Kimi K2.5. Kimi K2.5 gives you the larger context window at 256K, compared with 200K for Claude Haiku 4.5.

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 Claude Haiku 4.5 and Kimi K2.5
CategoryClaude Haiku 4.5ΔKimi K2.5
MathClaude Haiku 4.54.9Margin→ 55.7Kimi K2.560.6
CodingClaude Haiku 4.573.3Margin← 13.9Kimi K2.559.4
AgenticClaude Haiku 4.5Not measuredMarginNo overlapKimi K2.555.0
ReasoningClaude Haiku 4.5Not measuredMarginNo overlapKimi K2.561.0
KnowledgeClaude Haiku 4.5Not measuredMarginNo overlapKimi K2.556.9
MultilingualClaude Haiku 4.5Not measuredMarginNo overlapKimi K2.582.3
MultimodalClaude Haiku 4.5Not measuredMarginNo overlapKimi K2.578.5
Inst. FollowingClaude Haiku 4.5Not measuredMarginNo overlapKimi K2.593.9

Decisive benchmark drivers

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

More
A · Claude Haiku 4.5B · Kimi K2.5

  1. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 5.903%B 27.900%
    Winner: Kimi K2.5Δ 22
    FrontierMath v2 (Tiers 1-3): Claude Haiku 4.5 scored 5.903%; Kimi K2.5 scored 27.900%. Kimi K2.5 wins this benchmark.

  2. SWE-bench Verified

    Coding
    Source ↗
    A 73.3%B 76.8%
    Winner: Kimi K2.5Δ 3.5
    SWE-bench Verified: Claude Haiku 4.5 scored 73.3%; Kimi K2.5 scored 76.8%. Kimi K2.5 wins this benchmark.

  3. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 2.083%B 4.200%
    Winner: Kimi K2.5Δ 2.1
    FrontierMath v2 (Tier 4): Claude Haiku 4.5 scored 2.083%; 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.

MetricClaude Haiku 4.5Kimi K2.5Comparison
Input / output priceUSD per 1M tokensClaude Haiku 4.5$1 input / $5 outputKimi K2.5$0.6 input / $3 outputKimi K2.5 has the lower combined listed price.
Generation speedtokens per secondClaude Haiku 4.5Not availableKimi K2.545 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Haiku 4.5Not availableKimi K2.52.38 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Haiku 4.5200KKimi K2.5256KKimi K2.5 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude Haiku 4.5Kimi K2.5Result
JobBenchSource 16.0%8.7%Claude Haiku 4.5 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
τ²-bench resultsSource —95.9%Not comparable
APEX-Agents-AASource —11.5%Not comparable
Gert LabsSource —45.88%Not comparable
ResearchClawBenchSource —14.0%Not comparable
AA Agentic IndexSource —21.7%Not comparable
GDPval-AASource —25.4%Not comparable
GDPval-AASource —1009Not comparable
CodingClaude Haiku 4.5 wins
BenchmarkClaude Haiku 4.5Kimi K2.5Result
SWE-bench VerifiedSource 73.3%76.8%Kimi K2.5 leads
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-SciCodeSource —49.0%Not comparable
AA Coding IndexSource —46.8%Not comparable
Reasoning
BenchmarkClaude Haiku 4.5Kimi K2.5Result
LongBench v2Source —61%Not comparable
AA-LCRSource —65.3%Not comparable
CritPtSource —3.1%Not comparable
Knowledge
BenchmarkClaude Haiku 4.5Kimi 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
MathKimi K2.5 wins
BenchmarkClaude Haiku 4.5Kimi K2.5Result
FrontierMath v2 (Tiers 1-3)Source 5.903%27.900%Kimi K2.5 leads
FrontierMath v2 (Tier 4)Source 2.083%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
BenchmarkClaude Haiku 4.5Kimi K2.5Result
MMLU-ProXSource —82.3%Not comparable
NOVA-63Source —56.0%Not comparable
Multimodal
BenchmarkClaude Haiku 4.5Kimi K2.5Result
Design Arena WebsiteSource 11521279Kimi 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
BenchmarkClaude Haiku 4.5Kimi K2.5Result
IFEvalSource —93.9%Not comparable
AA-IFBenchSource —70.2%Not comparable
Frequently Asked Questions (3)

Which is better, Claude Haiku 4.5 or Kimi K2.5?

Kimi K2.5 is ahead on BenchLM's BenchAlign leaderboard, 59.66 to 56.58. The biggest single separator in this matchup is FrontierMath v2 (Tiers 1-3), where the scores are 5.903% and 27.900%.

Which is better for coding, Claude Haiku 4.5 or Kimi K2.5?

Claude Haiku 4.5 has the edge for coding in this comparison, averaging 73.3 versus 59.4. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Claude Haiku 4.5 or Kimi K2.5?

Kimi K2.5 has the edge for math in this comparison, averaging 60.6 versus 4.9. 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.

Claude Haiku 4.5
API / mo$4,500
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

Anthropic 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.