Skip to main content

Model comparison

GPT-5.4 vs Kimi K2.5

Data verified

Head-to-head evidence from 35 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

OpenAI
74.24/100
Margin
14.6pts
← winning
Moonshot AI
59.66/100
2 category wins3 category wins

Public leaderboard positions: GPT-5.4 #8 (Supported); Kimi K2.5 #54 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.4 and Kimi K2.5 share 35 comparable benchmark results. 5 of 8 categories are comparable. 17 results are unique to GPT-5.4; 28 to Kimi K2.5.

Updated July 20, 2026
Shared results
35
GPT-5.4 only
17
Kimi K2.5 only
28
Comparable categories
5 / 8

Pick GPT-5.4 if you want the stronger benchmark profile. Kimi K2.5 only becomes the better choice if mathematics is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 35 shared benchmark results across 7 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

GPT-5.4 is clearly ahead on the BenchAlign aggregate, 74.24 to 59.66. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.4's sharpest advantage is in agentic, where it averages 77.2 against 55. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 75.1% to 50.8%. Kimi K2.5 does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

GPT-5.4 is also the more expensive model on tokens at $2.50 input / $15.00 output per 1M tokens, versus $0.60 input / $3.00 output per 1M tokens for Kimi K2.5. That is roughly 5.0x on output cost alone. GPT-5.4 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. GPT-5.4 gives you the larger context window at 1.05M, compared with 256K for Kimi K2.5.

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 GPT-5.4 and Kimi K2.5
CategoryGPT-5.4ΔKimi K2.5
AgenticGPT-5.477.2Margin 22.2Kimi K2.555.0
MathGPT-5.442.5Margin 18.1Kimi K2.560.6
MultimodalGPT-5.473.2Margin 5.3Kimi K2.578.5
CodingGPT-5.457.7Margin 1.7Kimi K2.559.4
KnowledgeGPT-5.457.6Margin 0.7Kimi K2.556.9
ReasoningGPT-5.4Not measuredMarginNo overlapKimi K2.561.0
MultilingualGPT-5.4Not measuredMarginNo overlapKimi K2.582.3
Inst. FollowingGPT-5.4Not measuredMarginNo overlapKimi K2.593.9

Decisive benchmark drivers

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

More
A · GPT-5.4B · Kimi K2.5
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 75.1%B 50.8%
    Winner: GPT-5.4Δ 24.3
    Terminal-Bench 2.0: GPT-5.4 scored 75.1%; Kimi K2.5 scored 50.8%. GPT-5.4 wins this benchmark.
  2. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 27.100%B 4.200%
    Winner: GPT-5.4Δ 22.9
    FrontierMath v2 (Tier 4): GPT-5.4 scored 27.100%; Kimi K2.5 scored 4.200%. GPT-5.4 wins this benchmark.
  3. BrowseComp

    Agentic
    Source ↗
    A 82.7%B 60.6%
    Winner: GPT-5.4Δ 22.1
    BrowseComp: GPT-5.4 scored 82.7%; Kimi K2.5 scored 60.6%. GPT-5.4 wins this benchmark.
  4. HLE

    Knowledge
    Source ↗
    A 52.1%B 30.1%
    Winner: GPT-5.4Δ 22
    HLE: GPT-5.4 scored 52.1%; Kimi K2.5 scored 30.1%. GPT-5.4 wins this benchmark.
  5. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 47.600%B 27.900%
    Winner: GPT-5.4Δ 19.7
    FrontierMath v2 (Tiers 1-3): GPT-5.4 scored 47.600%; Kimi K2.5 scored 27.900%. GPT-5.4 wins this benchmark.

Operational comparison

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

MetricGPT-5.4Kimi K2.5Comparison
Input / output priceUSD per 1M tokensGPT-5.4$2.5 input / $15 outputKimi K2.5$0.6 input / $3 outputKimi K2.5 has the lower combined listed price.
Generation speedtokens per secondGPT-5.474 tok/sKimi K2.545 tok/sGPT-5.4 has the higher measured throughput.
First-answer latencyseconds to first tokenGPT-5.4151.79 sKimi K2.52.38 sKimi K2.5 reaches the first token sooner.
Context windowmaximum listed tokensGPT-5.41.05MKimi K2.5256KGPT-5.4 lists the larger context window.

Benchmark Deep Dive

AgenticGPT-5.4 wins
BenchmarkGPT-5.4Kimi K2.5Result
Terminal-Bench 2.0Source 75.1%50.8%GPT-5.4 leads
CyberGymSource 79.0%Not comparable
BrowseCompSource 82.7%60.6%GPT-5.4 leads
OSWorld-VerifiedSource 75%Not comparable
MCP AtlasSource 70.6%29.5%GPT-5.4 leads
ToolathlonSource 54.6%27.8%GPT-5.4 leads
τ²-bench resultsSource 87.1%95.9%Kimi K2.5 leads
Claw-EvalSource 60.3%52.3%GPT-5.4 leads
DeepSearchQASource 73.6%77.1%Kimi K2.5 leads
AA Agentic IndexSource 41.1%21.7%GPT-5.4 leads
APEX-Agents-AASource 33.3%11.5%GPT-5.4 leads
GDPval-AASource 44.7%25.4%GPT-5.4 leads
GDPval-AASource 13951009GPT-5.4 leads
Gert LabsSource 64.89%45.88%GPT-5.4 leads
ResearchClawBenchSource 15.3%14.0%GPT-5.4 leads
JobBenchSource 38.9%8.7%GPT-5.4 leads
ExploitGymSource 6.0%Not comparable
QwenClawBenchSource 54.3%Not comparable
τ³-bench resultsSource 65.7%Not comparable
DeepPlanningSource 14.4%Not comparable
MCP-TasksSource 59.1%Not comparable
WideResearchSource 72.7%Not comparable
CodingKimi K2.5 wins
BenchmarkGPT-5.4Kimi K2.5Result
LiveCodeBench ProSource 87.5%Not comparable
SWE-bench ProSource 57.7%50.7%GPT-5.4 leads
React Native EvalsSource 85.3%77.2%GPT-5.4 leads
Vibe Code BenchSource 67.42%Not comparable
AA Coding IndexSource 71.0%46.8%GPT-5.4 leads
AA-SciCodeSource 56.6%49.0%GPT-5.4 leads
SWE-bench VerifiedSource 76.8%Not comparable
SWE-bench Verified*Source 70.8%Not comparable
LiveCodeBench v6Source 85.0%Not comparable
SWE MultilingualSource 73%Not comparable
SWE-RebenchSource 58.5%Not comparable
SciCodeSource 48.7%Not comparable
Reasoning
BenchmarkGPT-5.4Kimi K2.5Result
AA-LCRSource 74.0%65.3%GPT-5.4 leads
CritPtSource 23.4%3.1%GPT-5.4 leads
LongBench v2Source 61%Not comparable
KnowledgeGPT-5.4 wins
BenchmarkGPT-5.4Kimi K2.5Result
GPQASource 92.8%87.6%GPT-5.4 leads
HLESource 52.1%30.1%GPT-5.4 leads
HLE w/o toolsSource 39.8%Not comparable
GPQA-DSource 92.8%87.6%GPT-5.4 leads
HealthBench HardSource 40.1%Not comparable
MedXpertQA (Text)Source 59.6%Not comparable
Artificial Analysis Intelligence IndexSource 51.4%35.4%GPT-5.4 leads
AA-GPQA DiamondSource 92.0%87.9%GPT-5.4 leads
AA-HLESource 41.6%29.4%GPT-5.4 leads
AA-Omniscience IndexSource 5.7%-8.1%GPT-5.4 leads
AA-Omniscience AccuracySource 50.0%34.3%GPT-5.4 leads
AA-Omniscience Hallucination RateSource 88.6%64.6%Kimi K2.5 leads
HealthBench ProfessionalSource 48.1%Not comparable
SuperGPQASource 69.2%Not comparable
MMLU-ProSource 87.1%Not comparable
MMLU-Pro (Arcee)Source 87.1%Not comparable
MathKimi K2.5 wins
BenchmarkGPT-5.4Kimi K2.5Result
FrontierMath v2 (Tiers 1-3)Source 47.600%27.900%GPT-5.4 leads
FrontierMath v2 (Tier 4)Source 27.100%4.200%GPT-5.4 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
BenchmarkGPT-5.4Kimi K2.5Result
MMLU-ProXSource 82.3%Not comparable
NOVA-63Source 56.0%Not comparable
MultimodalKimi K2.5 wins
BenchmarkGPT-5.4Kimi K2.5Result
MMMU-ProSource 81.2%78.5%GPT-5.4 leads
OfficeQA ProSource 53.2%Not comparable
MMMU-Pro w/ PythonSource 82.1%Not comparable
CharXivSource 82.8%Not comparable
ERQASource 65.4%Not comparable
SimpleVQASource 61.1%Not comparable
ScreenSpot ProSource 85.4%Not comparable
ZeroBenchSource 41.0%Not comparable
MedXpertQA (MM)Source 77.1%Not comparable
AA-MMMU-ProSource 78.4%75.4%GPT-5.4 leads
Design Arena WebsiteSource 12521282Kimi K2.5 leads
Video-MMESource 87.4%Not comparable
MMVUSource 80.4%Not comparable
VideoMMMUSource 86.6%Not comparable
Inst. Following
BenchmarkGPT-5.4Kimi K2.5Result
AA-IFBenchSource 73.9%70.2%GPT-5.4 leads
IFEvalSource 93.9%Not comparable
Frequently Asked Questions (6)

Which is better, GPT-5.4 or Kimi K2.5?

GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 59.66. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 75.1% and 50.8%.

Which is better for knowledge tasks, GPT-5.4 or Kimi K2.5?

GPT-5.4 has the edge for knowledge tasks in this comparison, averaging 57.6 versus 56.9. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.4 or Kimi K2.5?

Kimi K2.5 has the edge for coding in this comparison, averaging 59.4 versus 57.7. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.4 or Kimi K2.5?

Kimi K2.5 has the edge for math in this comparison, averaging 60.6 versus 42.5. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.4 or Kimi K2.5?

GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77.2 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, GPT-5.4 or Kimi K2.5?

Kimi K2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 78.5 versus 73.2. Inside this category, Design Arena Website 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.

GPT-5.4
API / mo$13,125
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 20, 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.