Skip to main content
BenchLM
Data

GPT-5.2-Codex vs Kimi K3

Updated November 17, 2026. Rank says Kimi K3 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Kimi K3 has the higher public point estimate, 67 versus 54.5. Their conditional score ranges overlap. These ranges do not establish rank confidence. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
OpenAI logo

OpenAI

54.5/100

Estimated · Public rank #71

Conditional range 44.8–64.2

Model B
Moonshot AI logo

Moonshot AI

67/100

Supported · Public rank #20

90% interval 61.6–72.4

API price per 1M tokens

GPT-5.2-Codex: $1.75 input / $14 output

Kimi K3: $3 input / $15 output

Context window

GPT-5.2-Codex: 400K

Kimi K3: 1.05M

Released

GPT-5.2-Codex: December 18, 2025

Kimi K3: July 16, 2026

Shared results
3
GPT-5.2-Codex only
3
Kimi K3 only
57
Like-for-like categories
1 / 8
Estimated: GPT-5.2-Codex · Supported: Kimi K3. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Kimi K3

    Kimi K3 has the higher public coding point estimate, 56.3 to 45.1, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Long documents

    Prompts that approach the documented context limit

    Kimi K3

    Kimi K3 has the larger documented context window.

    Confidence: documented
  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.2-Codex

    GPT-5.2-Codex has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
Show secondary and unsupported calls
  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Kimi K3

    Kimi K3 has the lower estimated token cost for this stated workload. GPT-5.2-Codex has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback
  • Repository review cost

    50K fresh input + 3K output tokens

    GPT-5.2-Codex

    GPT-5.2-Codex has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    GPT-5.2-Codex is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

45.1GPT-5.2-Codex56.3Kimi K3

Like-for-like · BenchAlign v5.8

Kimi K3 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Coding

Like-for-like
GPT-5.2-Codex
45.1
Supported · #60/163
Kimi K3
56.3
Supported · #23/163
Basis
BenchAlign v5.8 lane · 4 vs 18 public rows
Reading
Kimi K3 leads · intervals overlap

Agentic

Directional only
GPT-5.2-Codex
43.7
Estimated · #72/140
Kimi K3
65.1
Supported · #21/140
Basis
BenchAlign v5.8 lane · 2 vs 19 public rows
Reading
Directional only

Reasoning

Directional only
GPT-5.2-Codex
43.6
Estimated · #76/161
Kimi K3
65.4
Supported · #21/161
Basis
BenchAlign v5.8 lane · 0 vs 2 public rows
Reading
Directional only

Knowledge

Directional only
GPT-5.2-Codex
56.8
Estimated · #60/181
Kimi K3
67.5
Supported · #20/181
Basis
BenchAlign v5.8 lane · 0 vs 6 public rows
Reading
Directional only

Multimodal

Not comparable
GPT-5.2-Codex
Not ranked
Kimi K3
66.7
Estimated · #19/67
Basis
BenchAlign v5.8 lane · 0 vs 14 public rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.2-Codex
Not ranked
Kimi K3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.2-Codex
93.8
#5/157
Kimi K3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
GPT-5.2-Codex
Not ranked
Kimi K3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

GPT-5.2-Codex
$0.00875
Fits in one request
Kimi K3
$0.0105
Fits in one request

GPT-5.2-Codex has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5.2-Codex
$0.1295
Fits in one request
Kimi K3
$0.195
Fits in one request

GPT-5.2-Codex has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

GPT-5.2-Codex
$0.525
Fits in one request
Cached input priced at the published list-input rate
Kimi K3
$0.27
Fits in one request

Kimi K3 has the lower modeled cost

GPT-5.2-Codex has no published cached-input rate, so cached tokens use its listed input rate.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

GPT-5.2-Codex
$45.50
per month
Kimi K3
$60.00
per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 17, 2026.

GPT-5.2-CodexKimi K3

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 27 models score at least as high as GPT-5.2-Codex for the same price or less. The nearest is GPT-5.3 Codex (score 61.4, also $14.00 per 1M output tokens).
  • 3 cheaper models score at least as high as Kimi K3. The nearest is Gemini 4 Carbon (score 85.1, $10.00 per 1M output tokens).

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See GPT-5.2-Codex on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Context window

Maximum documented context; output-token limits may be lower.

GPT-5.2-Codex

400K

Kimi K3

1.05M

API model ID

GPT-5.2-Codex

Not sourced

Kimi K3

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

GPT-5.2-Codex

Not published

Kimi K3

$0.3 per 1M cached input tokens

Provider availability

GPT-5.2-Codex

Not sourced

Kimi K3

Not sourced

Reasoning profile

GPT-5.2-Codex

Reasoning

Kimi K3

Reasoning

Weight access

GPT-5.2-Codex

Proprietary

Kimi K3

Open Weight

License

GPT-5.2-Codex

Proprietary

Kimi K3

Open Weight

Release date

GPT-5.2-Codex

2025-12-18

Kimi K3

2026-07-16

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Kimi K3 has the higher public point estimate, 67 versus 54.5. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
Repository review: $0.1295 vs $0.195. Cache-heavy agent loop: $0.525 vs $0.27.
Context tradeoff
Kimi K3 has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-5.2-Codex or Kimi K3?

Kimi K3 has the higher public point estimate, 67 versus 54.5. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GPT-5.2-Codex or Kimi K3?

Kimi K3 has the higher public coding point estimate, 56.3 to 45.1, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which is better for agentic tasks, GPT-5.2-Codex or Kimi K3?

Kimi K3 scores higher for agentic tasks on the public lane, 65.1 to 43.7. GPT-5.2-Codex is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, GPT-5.2-Codex or Kimi K3?

For the stated presets, chat costs $0.00875 on GPT-5.2-Codex and $0.0105 on Kimi K3; repository review costs $0.1295 and $0.195; the cache-heavy agent loop costs $0.525 and $0.27. GPT-5.2-Codex has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-5.2-Codex or Kimi K3?

Kimi K3 has the larger documented context window: 1.05M, compared with 400K.

Self-host vs API cost

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

GPT-5.2-Codex
API / mo$11,813
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K3
API / mo$13,500
Self-host / mo$57,606
Break-evenNot reached at 70% load
Model the full break-even

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence63 rows

Agentic

  • Gert Labs

    GPT-5.2-Codex51.79%
    Source
    Kimi K3—

    Not directly comparable

  • JobBench

    GPT-5.2-Codex26.0%
    Source
    Kimi K352.9%
    Source

    Kimi K3 leads this result

  • Terminal-Bench 4.1

    GPT-5.2-Codex—
    Kimi K323.00%
    Source

    Not directly comparable

  • Finch

    GPT-5.2-Codex—
    Kimi K377.3%
    Source

    Not directly comparable

  • b3 Agent Security

    GPT-5.2-Codex—
    Kimi K388.0%
    Source

    Not directly comparable

  • Cyber Misuse Refusal

    GPT-5.2-Codex—
    Kimi K394.0%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    GPT-5.2-Codex—
    Kimi K388.3%
    Source

    Not directly comparable

  • BrowseComp

    GPT-5.2-Codex—
    Kimi K391.2%
    Source

    Not directly comparable

  • DeepSearchQA

    GPT-5.2-Codex—
    Kimi K395.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    GPT-5.2-Codex—
    Kimi K373.2%
    Source

    Not directly comparable

  • MCP Atlas

    GPT-5.2-Codex—
    Kimi K384.2%
    Source

    Not directly comparable

  • AutomationBench

    GPT-5.2-Codex—
    Kimi K330.8%
    Source

    Not directly comparable

  • APEX-Agents

    GPT-5.2-Codex—
    Kimi K337.6%
    Source

    Not directly comparable

  • SpreadsheetBench 2

    GPT-5.2-Codex—
    Kimi K334.8%
    Source

    Not directly comparable

  • DECK-Bench

    GPT-5.2-Codex—
    Kimi K373.5%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GPT-5.2-Codex—
    Kimi K380.9%
    Source

    Not directly comparable

  • ApprenticeBench

    GPT-5.2-Codex—
    Kimi K318%
    Source

    Not directly comparable

  • Hermes Index

    GPT-5.2-Codex—
    Kimi K339.2%
    Source

    Not directly comparable

  • Hermes Bench

    GPT-5.2-Codex—
    Kimi K371.5%
    Source

    Not directly comparable

  • MazeBench

    GPT-5.2-Codex—
    Kimi K31%
    Source

    Not directly comparable

Coding

  • Vibe Code Bench

    GPT-5.2-Codex37.91%
    Source
    Kimi K3—

    Not directly comparable

  • LiveCodeBench (Vals)

    GPT-5.2-Codex88.0%
    Source
    Kimi K387.2%
    Source

    GPT-5.2-Codex leads this result

  • SWE-bench (Vals)

    GPT-5.2-Codex72.4%
    Source
    Kimi K393.4%
    Source

    Kimi K3 leads this result

  • PostTrainBench v1

    GPT-5.2-Codex17.2%
    Source
    Kimi K3—

    Not directly comparable

  • ScarfBench

    GPT-5.2-Codex—
    Kimi K361.3%
    Source

    Not directly comparable

  • DeepSWE

    GPT-5.2-Codex—
    Kimi K367.5%
    Source

    Not directly comparable

  • CursorBench 3.2

    GPT-5.2-Codex—
    Kimi K360.8%
    Source

    Not directly comparable

  • FrontierSWE

    GPT-5.2-Codex—
    Kimi K381.2%
    Source

    Not directly comparable

  • ProgramBench

    GPT-5.2-Codex—
    Kimi K377.8%
    Source

    Not directly comparable

  • Kimi Code Bench v2

    GPT-5.2-Codex—
    Kimi K372.9%
    Source

    Not directly comparable

  • sweMarathon

    GPT-5.2-Codex—
    Kimi K342%
    Source

    Not directly comparable

  • PostTrainBench (lab runs)

    GPT-5.2-Codex—
    Kimi K336.6%
    Source

    Not directly comparable

  • MLS-Bench Lite

    GPT-5.2-Codex—
    Kimi K348.3%
    Source

    Not directly comparable

  • VulcanBench v3

    GPT-5.2-Codex—
    Kimi K373.7%
    Source

    Not directly comparable

  • OpenHarmony Bench v1.0

    GPT-5.2-Codex—
    Kimi K357.3%
    Source

    Not directly comparable

  • FrontierSWE v2

    GPT-5.2-Codex—
    Kimi K325.9%
    Source

    Not directly comparable

  • PostTrainBench v1.1

    GPT-5.2-Codex—
    Kimi K332.0%
    Source

    Not directly comparable

  • Bug Hunt Bench

    GPT-5.2-Codex—
    Kimi K321.0 fixes
    Source

    Not directly comparable

  • FrontierCode 2.0

    GPT-5.2-Codex—
    Kimi K318.9%
    Source

    Not directly comparable

  • PostTrainBench

    GPT-5.2-Codex—
    Kimi K331.5%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    GPT-5.2-Codex—
    Kimi K394.50%
    Source

    Not directly comparable

  • ARC-AGI-2

    GPT-5.2-Codex—
    Kimi K360.4%
    Source

    Not directly comparable

Multimodal

  • ExtractBench (LlamaIndex)

    GPT-5.2-Codex—
    Kimi K383.17%
    Source

    Not directly comparable

  • OfficeQA Pro

    GPT-5.2-Codex—
    Kimi K363.3%
    Source

    Not directly comparable

  • MMMU-Pro

    GPT-5.2-Codex—
    Kimi K381.6%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    GPT-5.2-Codex—
    Kimi K383.4%
    Source

    Not directly comparable

  • CharXiv w/o tools

    GPT-5.2-Codex—
    Kimi K384.8%
    Source

    Not directly comparable

  • CharXiv

    GPT-5.2-Codex—
    Kimi K391.3%
    Source

    Not directly comparable

  • MathVision

    GPT-5.2-Codex—
    Kimi K394.3%
    Source

    Not directly comparable

  • MathVision w/ Python

    GPT-5.2-Codex—
    Kimi K397.8%
    Source

    Not directly comparable

  • BabyVision w/ Python

    GPT-5.2-Codex—
    Kimi K385.7%
    Source

    Not directly comparable

  • ZeroBench

    GPT-5.2-Codex—
    Kimi K323.0%
    Source

    Not directly comparable

  • ZeroBench w/ Python

    GPT-5.2-Codex—
    Kimi K341.0%
    Source

    Not directly comparable

  • WorldVQA ForceAnswer

    GPT-5.2-Codex—
    Kimi K351.0%
    Source

    Not directly comparable

  • OmniDocBench

    GPT-5.2-Codex—
    Kimi K391.1%
    Source

    Not directly comparable

  • PerceptionBench

    GPT-5.2-Codex—
    Kimi K358.5%
    Source

    Not directly comparable

Knowledge

  • GPQA

    GPT-5.2-Codex—
    Kimi K393.5%
    Source

    Not directly comparable

  • GPQA-D

    GPT-5.2-Codex—
    Kimi K393.5%
    Source

    Not directly comparable

  • HLE

    GPT-5.2-Codex—
    Kimi K356%
    Source

    Not directly comparable

  • HLE w/o tools

    GPT-5.2-Codex—
    Kimi K343.5%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    GPT-5.2-Codex—
    Kimi K392.9%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    GPT-5.2-Codex—
    Kimi K388.0%
    Source

    Not directly comparable

Instruction following

  • Gray Swan IPI (15 attempts)

    GPT-5.2-Codex—
    Kimi K352.7%
    Source

    Not directly comparable

63 public results · 3 shared

Watch GPT-5.2-Codex vs Kimi K3

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 17, 2026