Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start the free Radar Brief
BenchLM
OpenAI logo
Model A
GPT-5.4 nano

OpenAI

66.63/100

Supported · Public rank #32

90% interval 55.8–77.5

GPT-5.4 nano vs Kimi K2.6

Updated August 27, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Moonshot AI logo
Model B
Kimi K2.6

Moonshot AI

60.14/100

Estimated · Public rank #66

90% interval 50.3–70.0

Decision reading

GPT-5.4 nano has the higher public score estimate, 66.63 versus 60.14, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

11 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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.

  • Long documents

    Prompts that approach the documented context limit

    GPT-5.4 nano

    GPT-5.4 nano has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.4 nano

    GPT-5.4 nano has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

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

    GPT-5.4 nano

    GPT-5.4 nano has the lower estimated token cost for this stated workload. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    GPT-5.4 nano

    GPT-5.4 nano has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    Confidence: limited

What is actually comparable

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

Shared results
11
GPT-5.4 nano only
2
Kimi K2.6 only
21
Like-for-like categories
1 / 8

3 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Knowledge

Like-for-like
GPT-5.4 nano
43.8
Kimi K2.6
42.2
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 nano leads

Agentic

Directional only
GPT-5.4 nano
42.9
Kimi K2.6
73.5
Weighted basis
2 vs 3 rows
Reading
Directional only

Math

Directional only
GPT-5.4 nano
21.0
Kimi K2.6
67.1
Weighted basis
2 vs 4 rows
Reading
Directional only

Multimodal

Directional only
GPT-5.4 nano
66.1
Kimi K2.6
79.8
Weighted basis
1 vs 2 rows
Reading
Directional only

Coding

Not comparable
GPT-5.4 nano
Not measured
Kimi K2.6
64.4
Weighted basis
0 vs 3 rows
Reading
Not comparable

Reasoning

Not comparable
GPT-5.4 nano
Not measured
Kimi K2.6
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.4 nano
Not measured
Kimi K2.6
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.4 nano
Not measured
Kimi K2.6
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

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.

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-5.4 nano
$0.00082
Fits in one request
Kimi K2.6
$0.00295
Fits in one request

GPT-5.4 nano has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5.4 nano
$0.01375
Fits in one request
Kimi K2.6
$0.0595
Fits in one request

GPT-5.4 nano 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-5.4 nano
$0.0205
Fits in one request
Kimi K2.6
$0.249
Fits in one request
Cached input priced at the published list-input rate

GPT-5.4 nano has the lower modeled cost

Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.

Specification differences

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

Cached-input rate

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

GPT-5.4 nano

$0.02 per 1M cached input tokens

OpenAI pricing

Kimi K2.6

Not published

Provider availability

GPT-5.4 nano

Generally Available · OpenAI Responses API

OpenAI model catalog

Kimi K2.6

Not sourced

Reasoning profile

GPT-5.4 nano

Reasoning

Kimi K2.6

Reasoning

Weight access

GPT-5.4 nano

Proprietary

Kimi K2.6

Open Weight

License

GPT-5.4 nano

Proprietary

Kimi K2.6

Open Weight

Release date

GPT-5.4 nano

2026-03-17

Kimi K2.6

2026-04-20

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
GPT-5.4 nano has the higher public score estimate, 66.63 versus 60.14, but the 90% score intervals overlap.
Workload cost
Repository review: $0.01375 vs $0.0595. Cache-heavy agent loop: $0.0205 vs $0.249.
Context tradeoff
GPT-5.4 nano has the larger documented window (400K).

Run the same representative tasks against both endpoints before changing production traffic.

Self-host vs API cost

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

GPT-5.4 nano
API / mo$1,088
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.6
API / mo$3,713
Self-host / mo$18,221
Break-even326M/day
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 evidence34 rows

Agentic

  • Terminal-Bench 2.0

    GPT-5.4 nano46.3%
    Source
    Kimi K2.666.7%
    Source

    Kimi K2.6 leads this result

  • OSWorld-Verified

    GPT-5.4 nano39%
    Source
    Kimi K2.673.1%
    Source

    Kimi K2.6 leads this result

  • MCP Atlas

    GPT-5.4 nano56.1%
    Source
    Kimi K2.655.9%
    Source

    GPT-5.4 nano leads this result

  • Toolathlon

    GPT-5.4 nano35.5%
    Source
    Kimi K2.650%
    Source

    Kimi K2.6 leads this result

  • τ²-bench results

    GPT-5.4 nano92.5%
    Source
    Kimi K2.6—

    Not directly comparable

  • BrowseComp

    GPT-5.4 nano—
    Kimi K2.683.2%
    Source

    Not directly comparable

  • Claw-Eval

    GPT-5.4 nano—
    Kimi K2.662.3%
    Source

    Not directly comparable

  • DeepSearchQA

    GPT-5.4 nano—
    Kimi K2.692.5%
    Source

    Not directly comparable

  • WideResearch

    GPT-5.4 nano—
    Kimi K2.680.8%
    Source

    Not directly comparable

  • Gert Labs

    GPT-5.4 nano—
    Kimi K2.656.82%
    Source

    Not directly comparable

  • ResearchClawBench

    GPT-5.4 nano—
    Kimi K2.618.0%
    Source

    Not directly comparable

  • OSWorld 2.0

    GPT-5.4 nano—
    Kimi K2.64.6%
    Source

    Not directly comparable

Coding

  • Vibe Code Bench

    Shared source
    GPT-5.4 nano26.10%
    Kimi K2.637.89%

    Kimi K2.6 leads this result

  • SWE-bench Verified

    GPT-5.4 nano—
    Kimi K2.680.2%
    Source

    Not directly comparable

  • LiveCodeBench v6

    GPT-5.4 nano—
    Kimi K2.689.6%
    Source

    Not directly comparable

  • SWE-bench Pro

    GPT-5.4 nano—
    Kimi K2.658.6%
    Source

    Not directly comparable

  • SWE Multilingual

    GPT-5.4 nano—
    Kimi K2.676.7%
    Source

    Not directly comparable

  • SciCode

    GPT-5.4 nano—
    Kimi K2.652.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    GPT-5.4 nano—
    Kimi K2.666.7%
    Source

    Not directly comparable

  • cursorBench31

    GPT-5.4 nano—
    Kimi K2.647.6%
    Source

    Not directly comparable

Knowledge

  • GPQA

    GPT-5.4 nano82.8%
    Source
    Kimi K2.690.5%
    Source

    Kimi K2.6 leads this result

  • HLE

    GPT-5.4 nano37.7%
    Source
    Kimi K2.634.7%
    Source

    GPT-5.4 nano leads this result

  • HLE w/o tools

    GPT-5.4 nano24.3%
    Source
    Kimi K2.6—

    Not directly comparable

  • GPQA-D

    GPT-5.4 nano—
    Kimi K2.690.5%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    GPT-5.4 nano25.860%
    Kimi K2.638.966%

    Kimi K2.6 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    GPT-5.4 nano6.250%
    Kimi K2.614.580%

    Kimi K2.6 leads this result

  • AIME26

    GPT-5.4 nano—
    Kimi K2.696.4%
    Source

    Not directly comparable

  • HMMT Feb 2026

    GPT-5.4 nano—
    Kimi K2.692.7%
    Source

    Not directly comparable

  • MMAnswerBench

    GPT-5.4 nano—
    Kimi K2.686.0%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    GPT-5.4 nano66.1%
    Source
    Kimi K2.679.4%
    Source

    Kimi K2.6 leads this result

  • MMMU-Pro w/ Python

    GPT-5.4 nano69.5%
    Source
    Kimi K2.680.1%
    Source

    Kimi K2.6 leads this result

  • CharXiv

    GPT-5.4 nano—
    Kimi K2.680.4%
    Source

    Not directly comparable

  • MathVision

    GPT-5.4 nano—
    Kimi K2.687.4%
    Source

    Not directly comparable

  • V*

    GPT-5.4 nano—
    Kimi K2.696.9%
    Source

    Not directly comparable

Frequently asked questions

Which is better, GPT-5.4 nano or Kimi K2.6?

GPT-5.4 nano has the higher public score estimate, 66.63 versus 60.14, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, GPT-5.4 nano or Kimi K2.6?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, GPT-5.4 nano or Kimi K2.6?

The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which costs less, GPT-5.4 nano or Kimi K2.6?

For the stated presets, chat costs $0.00082 on GPT-5.4 nano and $0.00295 on Kimi K2.6; repository review costs $0.01375 and $0.0595; the cache-heavy agent loop costs $0.0205 and $0.249. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-5.4 nano or Kimi K2.6?

GPT-5.4 nano has the larger documented context window: 400K, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 27, 2026

Watch GPT-5.4 nano vs Kimi K2.6

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

Read a sample issue

Join 2,000+ readers.