Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
BenchLM
Google logo
Model A
Gemma 3 27B

Google

36.26/100

Supported · Public rank #217

90% interval 15.3–57.2

Gemma 3 27B vs Kimi K3

Updated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Moonshot AI logo
Model B
Kimi K3

Moonshot AI

74.82/100

Supported · Public rank #8

90% interval 71.4–78.2

Decision reading

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.

0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on XLinkedInSocial cardCSVJSON

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

    Kimi K3

    Kimi K3 has the larger documented context window.

    Confidence: documented

Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Gemma 3 27B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    Gemma 3 27B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

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

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Gemma 3 27B does not fit this workload in one request. Gemma 3 27B has no comparable published API token rate.

    Confidence: listed-rates

  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Gemma 3 27B does not fit this workload in one request. Gemma 3 27B has no comparable published API token rate.

    Confidence: listed-rates

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
0
Gemma 3 27B only
0
Kimi K3 only
44
Like-for-like categories
0 / 8

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

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, 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.

Agentic

Directional only
Gemma 3 27B
33.0
Estimated · #137/152
Kimi K3
71.9
Supported · #4/152
Basis
BenchAlign lane · 0 vs 12 public rows
Reading
Directional only

Coding

Directional only
Gemma 3 27B
33.3
Estimated · #132/151
Kimi K3
68.0
Supported · #6/151
Basis
BenchAlign lane · 0 vs 13 public rows
Reading
Directional only

Knowledge

Directional only
Gemma 3 27B
33.6
Estimated · #167/183
Kimi K3
72.0
Supported · #8/183
Basis
BenchAlign lane · 0 vs 6 public rows
Reading
Directional only

Reasoning

Not comparable
Gemma 3 27B
26.0
Unranked · 2 rankable rows
Kimi K3
78.5
#3/20
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Gemma 3 27B
Not ranked
Kimi K3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Gemma 3 27B
Not ranked
Kimi K3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Gemma 3 27B
30.8
Unranked · 1 rankable row
Kimi K3
89.5
#1/48
Basis
Provisional lane · 0 vs 3 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Gemma 3 27B
36.0
#109/123
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, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

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.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

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

Gemma 3 27B
Self-hosted; infrastructure cost varies
Fits in one request
Kimi K3
$0.0105
Fits in one request

Gemma 3 27B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Gemma 3 27B
Self-hosted; infrastructure cost varies
Does not fit in one request
Kimi K3
$0.195
Fits in one request

Gemma 3 27B does not fit this workload in one request. Gemma 3 27B has no comparable published API token rate.

Cache-heavy agent loop

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

Gemma 3 27B
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable
Kimi K3
$0.27
Fits in one request

Gemma 3 27B does not fit this workload in one request. Gemma 3 27B has no comparable published API token 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.

Gemma 3 27B

32K

Kimi K3

1.05M

API model ID

Gemma 3 27B

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.

Gemma 3 27B

No comparable hosted API rate

Kimi K3

$0.3 per 1M cached input tokens

Documented inputs

Gemma 3 27B

Not sourced

Kimi K3

Not sourced

Documented outputs

Gemma 3 27B

Not sourced

Kimi K3

Not sourced

Provider availability

Gemma 3 27B

Not sourced

Kimi K3

Not sourced

Reasoning profile

Gemma 3 27B

Non-Reasoning

Kimi K3

Reasoning

Weight access

Gemma 3 27B

Open Weight

Kimi K3

Pending

License

Gemma 3 27B

Open Weight

Kimi K3

Pending

Release date

Gemma 3 27B

2025-03-12

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
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Kimi K3 has the larger documented window (1.05M).

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

Benchmark evidence

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

Browse raw public benchmark evidence44 rows

Agentic

  • Terminal-Bench 2.0

    Gemma 3 27B—
    Kimi K388.3%
    Source

    Not directly comparable

  • BrowseComp

    Gemma 3 27B—
    Kimi K391.2%
    Source

    Not directly comparable

  • DeepSearchQA

    Gemma 3 27B—
    Kimi K395.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Gemma 3 27B—
    Kimi K373.2%
    Source

    Not directly comparable

  • MCP Atlas

    Gemma 3 27B—
    Kimi K384.2%
    Source

    Not directly comparable

  • AutomationBench

    Gemma 3 27B—
    Kimi K330.8%
    Source

    Not directly comparable

  • JobBench

    Gemma 3 27B—
    Kimi K352.9%
    Source

    Not directly comparable

  • APEX-Agents

    Gemma 3 27B—
    Kimi K337.6%
    Source

    Not directly comparable

  • SpreadsheetBench 2

    Gemma 3 27B—
    Kimi K334.8%
    Source

    Not directly comparable

  • DECK-Bench

    Gemma 3 27B—
    Kimi K373.5%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Gemma 3 27B—
    Kimi K380.9%
    Source

    Not directly comparable

  • ApprenticeBench

    Gemma 3 27B—
    Kimi K318%
    Source

    Not directly comparable

Coding

  • DeepSWE

    Gemma 3 27B—
    Kimi K367.5%
    Source

    Not directly comparable

  • cursorBench32

    Gemma 3 27B—
    Kimi K360.8%
    Source

    Not directly comparable

  • FrontierSWE

    Gemma 3 27B—
    Kimi K381.2%
    Source

    Not directly comparable

  • ProgramBench

    Gemma 3 27B—
    Kimi K377.8%
    Source

    Not directly comparable

  • Kimi Code Bench v2

    Gemma 3 27B—
    Kimi K372.9%
    Source

    Not directly comparable

  • sweMarathon

    Gemma 3 27B—
    Kimi K342%
    Source

    Not directly comparable

  • PostTrain Bench

    Gemma 3 27B—
    Kimi K336.6%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Gemma 3 27B—
    Kimi K348.3%
    Source

    Not directly comparable

  • VulcanBench v3

    Gemma 3 27B—
    Kimi K373.7%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Gemma 3 27B—
    Kimi K357.3%
    Source

    Not directly comparable

  • FrontierSWE v2

    Gemma 3 27B—
    Kimi K325.9%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Gemma 3 27B—
    Kimi K387.2%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Gemma 3 27B—
    Kimi K393.4%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Gemma 3 27B—
    Kimi K393.5%
    Source

    Not directly comparable

  • GPQA-D

    Gemma 3 27B—
    Kimi K393.5%
    Source

    Not directly comparable

  • HLE

    Gemma 3 27B—
    Kimi K356%
    Source

    Not directly comparable

  • HLE w/o tools

    Gemma 3 27B—
    Kimi K343.5%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Gemma 3 27B—
    Kimi K392.9%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Gemma 3 27B—
    Kimi K388.0%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    Gemma 3 27B—
    Kimi K363.3%
    Source

    Not directly comparable

  • MMMU-Pro

    Gemma 3 27B—
    Kimi K381.6%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    Gemma 3 27B—
    Kimi K383.4%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Gemma 3 27B—
    Kimi K384.8%
    Source

    Not directly comparable

  • CharXiv

    Gemma 3 27B—
    Kimi K391.3%
    Source

    Not directly comparable

  • MathVision

    Gemma 3 27B—
    Kimi K394.3%
    Source

    Not directly comparable

  • MathVision w/ Python

    Gemma 3 27B—
    Kimi K397.8%
    Source

    Not directly comparable

  • BabyVision w/ Python

    Gemma 3 27B—
    Kimi K385.7%
    Source

    Not directly comparable

  • ZeroBench

    Gemma 3 27B—
    Kimi K323.0%
    Source

    Not directly comparable

  • ZeroBench w/ Python

    Gemma 3 27B—
    Kimi K341.0%
    Source

    Not directly comparable

  • WorldVQA ForceAnswer

    Gemma 3 27B—
    Kimi K351.0%
    Source

    Not directly comparable

  • OmniDocBench

    Gemma 3 27B—
    Kimi K391.1%
    Source

    Not directly comparable

  • PerceptionBench

    Gemma 3 27B—
    Kimi K358.5%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Gemma 3 27B or Kimi K3?

The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Gemma 3 27B or Kimi K3?

Kimi K3 scores higher for coding on the public lane, 68 to 33.3. Gemma 3 27B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Gemma 3 27B or Kimi K3?

Kimi K3 scores higher for agentic tasks on the public lane, 71.9 to 33. Gemma 3 27B 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, Gemma 3 27B or Kimi K3?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Gemma 3 27B or Kimi K3?

Kimi K3 has the larger documented context window: 1.05M, compared with 32K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 10, 2026

Watch Gemma 3 27B vs Kimi K3

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

Read a sample issue

Join 2,000+ readers.