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-4.1 nano

OpenAI

42.33/100

Estimated · Public rank #184

90% interval 30.8–53.8

GPT-4.1 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

Kimi K2.6 has the higher public score estimate, 60.14 versus 42.33, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

2 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-4.1 nano

    GPT-4.1 nano has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-4.1 nano

    GPT-4.1 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-4.1 nano

    GPT-4.1 nano has the lower estimated token cost for this stated workload. GPT-4.1 nano has no published cached-input rate, so cached tokens use its listed input rate. 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-4.1 nano

    GPT-4.1 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

    No shared weighted benchmark basis supports a winner.

    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
2
GPT-4.1 nano only
2
Kimi K2.6 only
30
Like-for-like categories
0 / 8

2 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

Directional only
GPT-4.1 nano
50.3
Kimi K2.6
42.2
Weighted basis
1 vs 2 rows
Reading
Directional only

Math

Directional only
GPT-4.1 nano
1.0
Kimi K2.6
67.1
Weighted basis
1 vs 4 rows
Reading
Directional only

Agentic

Not comparable
GPT-4.1 nano
Not measured
Kimi K2.6
73.5
Weighted basis
0 vs 3 rows
Reading
Not comparable

Coding

Not comparable
GPT-4.1 nano
Not measured
Kimi K2.6
64.4
Weighted basis
0 vs 3 rows
Reading
Not comparable

Reasoning

Not comparable
GPT-4.1 nano
Not measured
Kimi K2.6
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-4.1 nano
Not measured
Kimi K2.6
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
GPT-4.1 nano
Not measured
Kimi K2.6
79.8
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-4.1 nano
83.2
Kimi K2.6
Not measured
Weighted basis
1 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-4.1 nano
$0.0003
Fits in one request
Kimi K2.6
$0.00295
Fits in one request

GPT-4.1 nano has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-4.1 nano
$0.0062
Fits in one request
Kimi K2.6
$0.0595
Fits in one request

GPT-4.1 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-4.1 nano
$0.026
Fits in one request
Cached input priced at the published list-input rate
Kimi K2.6
$0.249
Fits in one request
Cached input priced at the published list-input rate

GPT-4.1 nano has the lower modeled cost

GPT-4.1 nano has no published cached-input rate, so cached tokens use its listed input rate. 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.

Context window

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

GPT-4.1 nano

1M

Kimi K2.6

256K

API model ID

GPT-4.1 nano

Not sourced

Kimi K2.6

Not sourced

Cached-input rate

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

GPT-4.1 nano

Not published

Kimi K2.6

Not published

Documented inputs

GPT-4.1 nano

Not sourced

Kimi K2.6

Not sourced

Documented outputs

GPT-4.1 nano

Not sourced

Kimi K2.6

Not sourced

Provider availability

GPT-4.1 nano

Not sourced

Kimi K2.6

Not sourced

Reasoning profile

GPT-4.1 nano

Non-Reasoning

Kimi K2.6

Reasoning

Weight access

GPT-4.1 nano

Proprietary

Kimi K2.6

Open Weight

License

GPT-4.1 nano

Proprietary

Kimi K2.6

Open Weight

Release date

GPT-4.1 nano

2025-04-14

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
Kimi K2.6 has the higher public score estimate, 60.14 versus 42.33, but the 90% score intervals overlap.
Workload cost
Repository review: $0.0062 vs $0.0595. Cache-heavy agent loop: $0.026 vs $0.249.
Context tradeoff
GPT-4.1 nano has the larger documented window (1M).

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-4.1 nano
API / mo$375
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-4.1 nano—
    Kimi K2.666.7%
    Source

    Not directly comparable

  • BrowseComp

    GPT-4.1 nano—
    Kimi K2.683.2%
    Source

    Not directly comparable

  • OSWorld-Verified

    GPT-4.1 nano—
    Kimi K2.673.1%
    Source

    Not directly comparable

  • Toolathlon

    GPT-4.1 nano—
    Kimi K2.650%
    Source

    Not directly comparable

  • MCP Atlas

    GPT-4.1 nano—
    Kimi K2.655.9%
    Source

    Not directly comparable

  • Claw-Eval

    GPT-4.1 nano—
    Kimi K2.662.3%
    Source

    Not directly comparable

  • DeepSearchQA

    GPT-4.1 nano—
    Kimi K2.692.5%
    Source

    Not directly comparable

  • WideResearch

    GPT-4.1 nano—
    Kimi K2.680.8%
    Source

    Not directly comparable

  • Gert Labs

    GPT-4.1 nano—
    Kimi K2.656.82%
    Source

    Not directly comparable

  • ResearchClawBench

    GPT-4.1 nano—
    Kimi K2.618.0%
    Source

    Not directly comparable

  • OSWorld 2.0

    GPT-4.1 nano—
    Kimi K2.64.6%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    GPT-4.1 nano—
    Kimi K2.680.2%
    Source

    Not directly comparable

  • LiveCodeBench v6

    GPT-4.1 nano—
    Kimi K2.689.6%
    Source

    Not directly comparable

  • SWE-bench Pro

    GPT-4.1 nano—
    Kimi K2.658.6%
    Source

    Not directly comparable

  • SWE Multilingual

    GPT-4.1 nano—
    Kimi K2.676.7%
    Source

    Not directly comparable

  • SciCode

    GPT-4.1 nano—
    Kimi K2.652.2%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    GPT-4.1 nano—
    Kimi K2.666.7%
    Source

    Not directly comparable

  • Vibe Code Bench

    GPT-4.1 nano—
    Kimi K2.637.89%
    Source

    Not directly comparable

  • cursorBench31

    GPT-4.1 nano—
    Kimi K2.647.6%
    Source

    Not directly comparable

Knowledge

  • MMLU

    GPT-4.1 nano80.1%
    Source
    Kimi K2.6—

    Not directly comparable

  • GPQA

    GPT-4.1 nano50.3%
    Source
    Kimi K2.690.5%
    Source

    Kimi K2.6 leads this result

  • GPQA-D

    GPT-4.1 nano—
    Kimi K2.690.5%
    Source

    Not directly comparable

  • HLE

    GPT-4.1 nano—
    Kimi K2.634.7%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    GPT-4.1 nano1.034%
    Kimi K2.638.966%

    Kimi K2.6 leads this result

  • AIME26

    GPT-4.1 nano—
    Kimi K2.696.4%
    Source

    Not directly comparable

  • HMMT Feb 2026

    GPT-4.1 nano—
    Kimi K2.692.7%
    Source

    Not directly comparable

  • MMAnswerBench

    GPT-4.1 nano—
    Kimi K2.686.0%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    GPT-4.1 nano—
    Kimi K2.614.580%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    GPT-4.1 nano—
    Kimi K2.679.4%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    GPT-4.1 nano—
    Kimi K2.680.1%
    Source

    Not directly comparable

  • CharXiv

    GPT-4.1 nano—
    Kimi K2.680.4%
    Source

    Not directly comparable

  • MathVision

    GPT-4.1 nano—
    Kimi K2.687.4%
    Source

    Not directly comparable

  • V*

    GPT-4.1 nano—
    Kimi K2.696.9%
    Source

    Not directly comparable

Instruction following

  • IFEval

    GPT-4.1 nano83.2%
    Source
    Kimi K2.6—

    Not directly comparable

Frequently asked questions

Which is better, GPT-4.1 nano or Kimi K2.6?

Kimi K2.6 has the higher public score estimate, 60.14 versus 42.33, 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-4.1 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-4.1 nano or Kimi K2.6?

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

Which costs less, GPT-4.1 nano or Kimi K2.6?

For the stated presets, chat costs $0.0003 on GPT-4.1 nano and $0.00295 on Kimi K2.6; repository review costs $0.0062 and $0.0595; the cache-heavy agent loop costs $0.026 and $0.249. GPT-4.1 nano has no published cached-input rate, so cached tokens use its listed input rate. Kimi K2.6 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-4.1 nano or Kimi K2.6?

GPT-4.1 nano has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 27, 2026

Watch GPT-4.1 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.