Skip to main content

Model comparison

Claude Opus 5 vs Kimi K2.5

Data verified

Head-to-head evidence from 21 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Anthropic
85.88/100
Margin
27.0pts
← winning
Moonshot AI
58.83/100
4 category wins1 category wins

Public leaderboard positions: Claude Opus 5 #1 (Estimated); Kimi K2.5 #59 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Opus 5 and Kimi K2.5 share 21 comparable benchmark results. 5 of 8 categories are comparable. 58 results are unique to Claude Opus 5; 42 to Kimi K2.5.

Updated July 24, 2026
Shared results
21
Claude Opus 5 only
58
Kimi K2.5 only
42
Comparable categories
5 / 8

Pick Claude Opus 5 if you want the stronger benchmark profile. Kimi K2.5 only becomes the better choice if multimodal & grounded is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 5 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Opus 5 is clearly ahead on the BenchAlign aggregate, 85.88 to 58.83. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Opus 5's sharpest advantage is in agentic, where it averages 90.8 against 55. The single biggest benchmark swing on the page is HLE, 64.7% to 30.1%. Kimi K2.5 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.

Claude Opus 5 is also the more expensive model on tokens at $5.00 input / $25.00 output per 1M tokens, versus $0.60 input / $3.00 output per 1M tokens for Kimi K2.5. That is roughly 8.3x on output cost alone. Claude Opus 5 is the reasoning model in the pair, while Kimi K2.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

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 Opus 5 and Kimi K2.5
CategoryClaude Opus 5ΔKimi K2.5
AgenticClaude Opus 590.8Margin 35.8Kimi K2.555.0
CodingClaude Opus 589.5Margin 30.1Kimi K2.559.4
ReasoningClaude Opus 590.4Margin 29.4Kimi K2.561.0
MultimodalClaude Opus 566.9Margin 11.6Kimi K2.578.5
KnowledgeClaude Opus 564.7Margin 7.8Kimi K2.556.9
MathClaude Opus 5Not measuredMarginNo overlapKimi K2.560.6
MultilingualClaude Opus 5Not measuredMarginNo overlapKimi K2.582.3
Inst. FollowingClaude Opus 5Not measuredMarginNo overlapKimi K2.593.9

Decisive benchmark drivers

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

More
A · Claude Opus 5B · Kimi K2.5
  1. HLE

    Knowledge
    Source ↗
    A 64.7%B 30.1%
    Winner: Claude Opus 5Δ 34.6
    HLE: Claude Opus 5 scored 64.7%; Kimi K2.5 scored 30.1%. Claude Opus 5 wins this benchmark.
  2. BrowseComp

    Agentic
    Source ↗
    A 90.8%B 60.6%
    Winner: Claude Opus 5Δ 30.2
    BrowseComp: Claude Opus 5 scored 90.8%; Kimi K2.5 scored 60.6%. Claude Opus 5 wins this benchmark.
  3. SWE-bench Pro

    Coding
    Source ↗
    A 79.2%B 50.7%
    Winner: Claude Opus 5Δ 28.5
    SWE-bench Pro: Claude Opus 5 scored 79.2%; Kimi K2.5 scored 50.7%. Claude Opus 5 wins this benchmark.
  4. SWE-bench Verified

    Coding
    Source ↗
    A 96%B 76.8%
    Winner: Claude Opus 5Δ 19.2
    SWE-bench Verified: Claude Opus 5 scored 96%; Kimi K2.5 scored 76.8%. Claude Opus 5 wins this benchmark.

Operational comparison

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

MetricClaude Opus 5Kimi K2.5Comparison
Input / output priceUSD per 1M tokensClaude Opus 5$5 input / $25 outputKimi K2.5$0.6 input / $3 outputKimi K2.5 has the lower combined listed price.
Generation speedtokens per secondClaude Opus 5Not availableKimi K2.545 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Opus 5Not availableKimi K2.52.38 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Opus 5Not availableKimi K2.5256KA complete context comparison is not available.

Benchmark Deep Dive

AgenticClaude Opus 5 wins
BenchmarkClaude Opus 5Kimi K2.5Result
FrontierBench v0.1Source 43.3%Not comparable
BrowseCompSource 90.8%60.6%Claude Opus 5 leads
HLE w/ toolsSource 64.7%Not comparable
DeepSearchQASource 95.0%77.1%Claude Opus 5 leads
DRACOSource 88.6%Not comparable
BrowseComp (10-agent, prerelease)Source 93.6%Not comparable
OSWorld 2.0Source 70.6%Not comparable
MCP AtlasSource 85.8%29.5%Claude Opus 5 leads
MCP-Atlas claim coverageSource 89.1%Not comparable
LAB all-pass (Anthropic harness)Source 23.58%Not comparable
LAB criterion-pass (Anthropic harness)Source 93.74%Not comparable
LAB all-pass (Harvey held-out)Source 11.7%Not comparable
LAB criterion-pass (Harvey held-out)Source 94.1%Not comparable
GDPval-AASource 18611003Claude Opus 5 leads
Toolathlon-VerifiedSource 80.6%Not comparable
Toolathlon Verified Pass@3Source 87.0%Not comparable
Toolathlon Verified Pass³Source 73.1%Not comparable
Toolathlon Verified avg. turnsSource 23.5 turnsNot comparable
AutomationBenchSource 26.0%Not comparable
AA Agentic IndexSource 55.3%21.7%Claude Opus 5 leads
GDPval-AASource 68.0%25.1%Claude Opus 5 leads
AA Tau3 BankingSource 30.3%Not comparable
AA BriefcaseSource 1720Not comparable
aaTerminalBench21Source 89.1%Not comparable
Terminal-Bench 2.0Source 50.8%Not comparable
Claw-EvalSource 52.3%Not comparable
QwenClawBenchSource 54.3%Not comparable
τ³-bench resultsSource 65.7%Not comparable
DeepPlanningSource 14.4%Not comparable
ToolathlonSource 27.8%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
JobBenchSource 8.7%Not comparable
CodingClaude Opus 5 wins
BenchmarkClaude Opus 5Kimi K2.5Result
SWE-bench VerifiedSource 96%76.8%Claude Opus 5 leads
SWE-bench ProSource 79.2%50.7%Claude Opus 5 leads
SWE MultilingualSource 89.5%73%Claude Opus 5 leads
SWE MultimodalSource 59.4%Not comparable
deepSweSource 68.8%Not comparable
FrontierCode 1.1 MainSource 53.4%Not comparable
FrontierCode 1.1 ExtendedSource 63.6%Not comparable
ProgramBench (episode 1)Source 83.0%Not comparable
ProgramBenchSource 93.0%Not comparable
cursorBench32Source 70.0%Not comparable
AA Coding IndexSource 78.0%46.8%Claude Opus 5 leads
AA-SciCodeSource 55.7%49.0%Claude Opus 5 leads
SWE-bench Verified*Source 70.8%Not comparable
LiveCodeBench v6Source 85.0%Not comparable
SWE-RebenchSource 58.5%Not comparable
React Native EvalsSource 77.2%Not comparable
SciCodeSource 48.7%Not comparable
ReasoningClaude Opus 5 wins
BenchmarkClaude Opus 5Kimi K2.5Result
ARC-AGI-1Source 97.50%Not comparable
ARC-AGI-2Source 90.4%Not comparable
ARC-AGI-3Source 30.2%Not comparable
AA-LCRSource 70.0%65.3%Claude Opus 5 leads
CritPtSource 29.1%3.1%Claude Opus 5 leads
LongBench v2Source 61%Not comparable
KnowledgeClaude Opus 5 wins
BenchmarkClaude Opus 5Kimi K2.5Result
HLESource 64.7%30.1%Claude Opus 5 leads
HLE w/o toolsSource 56.3%Not comparable
HealthBench (raw)Source 67.1%Not comparable
HealthBench (length-adjusted)Source 57.8%Not comparable
HealthBench ProfessionalSource 59.8%Not comparable
HealthBench Professional (raw)Source 73.4%Not comparable
BioMysteryBench (human-solvable)Source 90.1%Not comparable
BioMysteryBench (human-difficult)Source 49.4%Not comparable
SpatialBench VerifiedSource 72.5%Not comparable
SingleCellBenchSource 60.6%Not comparable
ProteinGym HardSource 47.7%Not comparable
Protein DesignSource 42.5%Not comparable
Organic chemistry V2Source 61.6%Not comparable
Protocols (troubleshooting)Source 61.1%Not comparable
Protocols (understanding)Source 78.4%Not comparable
Artificial Analysis Intelligence IndexSource 60.7%35.4%Claude Opus 5 leads
AA-GPQA DiamondSource 93.2%87.9%Claude Opus 5 leads
AA-HLESource 52.6%29.4%Claude Opus 5 leads
AA-Omniscience IndexSource 31.3%-8.1%Claude Opus 5 leads
AA-Omniscience AccuracySource 54.2%34.3%Claude Opus 5 leads
AA-Omniscience Hallucination RateSource 50.1%64.6%Claude Opus 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
Math
BenchmarkClaude Opus 5Kimi K2.5Result
IMO 2026Source 42/42Not comparable
RiemannBench (no tools)Source 60.0%Not comparable
RiemannBench (tools)Source 79.0%Not comparable
ArXivMath Jun. 2026 (no tools)Source 90.8%Not comparable
ArXivMath Jun. 2026 (tools)Source 91.3%Not comparable
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
BenchmarkClaude Opus 5Kimi K2.5Result
GMMLUSource 92.5%Not comparable
MILUSource 92.1%Not comparable
INCLUDESource 89.8%Not comparable
MMLU-ProXSource 82.3%Not comparable
NOVA-63Source 56.0%Not comparable
MultimodalKimi K2.5 wins
BenchmarkClaude Opus 5Kimi K2.5Result
Chartography (no tools)Source 29.6%Not comparable
Chartography (tools)Source 83.0%Not comparable
BenchCAD Vision2Code (no tools)Source 0.366Not comparable
BenchCAD Vision2Code (tools)Source 0.821Not comparable
GDP.pdf (no tools)Source 83.4%Not comparable
GDP.pdf (tools)Source 85.5%Not comparable
OfficeQASource 78.1%Not comparable
OfficeQA ProSource 66.9%Not comparable
AA-MMMU-ProSource 84.7%75.4%Claude Opus 5 leads
MMMU-ProSource 78.5%Not comparable
Video-MMESource 87.4%Not comparable
MMVUSource 80.4%Not comparable
VideoMMMUSource 86.6%Not comparable
Design Arena WebsiteSource 1279Not comparable
Inst. Following
BenchmarkClaude Opus 5Kimi K2.5Result
IFEvalSource 93.9%Not comparable
AA-IFBenchSource 70.2%Not comparable
Frequently Asked Questions (6)

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

Claude Opus 5 is ahead on BenchLM's BenchAlign leaderboard, 85.88 to 58.83. The biggest single separator in this matchup is HLE, where the scores are 64.7% and 30.1%.

Which is better for knowledge tasks, Claude Opus 5 or Kimi K2.5?

Claude Opus 5 has the edge for knowledge tasks in this comparison, averaging 64.7 versus 56.9. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

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

Claude Opus 5 has the edge for coding in this comparison, averaging 89.5 versus 59.4. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for reasoning, Claude Opus 5 or Kimi K2.5?

Claude Opus 5 has the edge for reasoning in this comparison, averaging 90.4 versus 61. Inside this category, CritPt is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Opus 5 or Kimi K2.5?

Claude Opus 5 has the edge for agentic tasks in this comparison, averaging 90.8 versus 55. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Claude Opus 5 or Kimi K2.5?

Kimi K2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 78.5 versus 66.9. Inside this category, AA-MMMU-Pro 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 Opus 5
API / mo$22,500
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

Last updated: July 24, 2026