Skip to main content
BenchLM

Alibaba GTE Reranker ModernBERT-base vs Kimi K3

Updated September 30, 2026. We do not rank this pair: at least one has no public score. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInSocial cardCSVJSON

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.

Model A

Alibaba-NLP

—

Evidence status unavailable

90% interval unavailable

Model B
Moonshot AI logo

Moonshot AI

72.12/100

Supported · Public rank #15

90% interval 68.8–75.4

Shared results
0
Alibaba GTE Reranker ModernBERT-base only
2
Kimi K3 only
48
Like-for-like categories
0 / 8
Supported: Kimi K3How 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.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

Show secondary and unsupported calls
  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Alibaba GTE Reranker ModernBERT-base is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited
  • Agentic work

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

    Not enough matched evidence

    Alibaba GTE Reranker ModernBERT-base is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited
  • Long documents

    Prompts that approach the documented context limit

    Not enough matched evidence

    A complete context comparison is not sourced.

    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

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

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

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

    Confidence: listed-rates

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.

—Alibaba GTE Reranker ModernBERT-base61.4Kimi K3

Not comparable · BenchAlign v5.8

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

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

Same basis rules as the category table below

What is actually comparable

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

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.

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, 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

Not comparable
Alibaba GTE Reranker ModernBERT-base
Not ranked
Kimi K3
67.8
Supported · #10/119
Basis
BenchAlign v5.8 lane · 0 vs 12 public rows
Reading
Not comparable

Coding

Not comparable
Alibaba GTE Reranker ModernBERT-base
Not ranked
Kimi K3
61.4
Supported · #18/144
Basis
BenchAlign v5.8 lane · 0 vs 14 public rows
Reading
Not comparable

Reasoning

Not comparable
Alibaba GTE Reranker ModernBERT-base
Not ranked
Kimi K3
65.8
#18/27
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Alibaba GTE Reranker ModernBERT-base
Not ranked
Kimi K3
89.4
#1/49
Basis
Provisional lane · 0 vs 3 weighted rows
Reading
Not comparable

Knowledge

Not comparable
Alibaba GTE Reranker ModernBERT-base
Not ranked
Kimi K3
67.8
Supported · #18/170
Basis
BenchAlign v5.8 lane · 0 vs 6 public rows
Reading
Not comparable

Multilingual

Not comparable
Alibaba GTE Reranker ModernBERT-base
Not ranked
Kimi K3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Alibaba GTE Reranker ModernBERT-base
Not ranked
Kimi K3
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Alibaba GTE Reranker ModernBERT-base
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, 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

Alibaba GTE Reranker ModernBERT-base
API rate not published
Fit state unavailable
Kimi K3
$0.0105
Fits in one request

Alibaba GTE Reranker ModernBERT-base has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Alibaba GTE Reranker ModernBERT-base
API rate not published
Fit state unavailable
Kimi K3
$0.195
Fits in one request

Alibaba GTE Reranker ModernBERT-base has no comparable published API token rate.

Cache-heavy agent loop

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

Alibaba GTE Reranker ModernBERT-base
API rate not published
Fit state unavailable
Cached-input rate unavailable
Kimi K3
$0.27
Fits in one request

Alibaba GTE Reranker ModernBERT-base has no comparable published API token rate.

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

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.

Alibaba GTE Reranker ModernBERT-base

Not sourced

Kimi K3

1.05M

API model ID

Alibaba GTE Reranker ModernBERT-base

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.

Alibaba GTE Reranker ModernBERT-base

No comparable hosted API rate

Provider pricing

Kimi K3

$0.3 per 1M cached input tokens

Documented inputs

Alibaba GTE Reranker ModernBERT-base

Not sourced

Kimi K3

Not sourced

Documented outputs

Alibaba GTE Reranker ModernBERT-base

Not sourced

Kimi K3

Not sourced

Provider availability

Alibaba GTE Reranker ModernBERT-base

Not sourced

Kimi K3

Not sourced

Reasoning profile

Alibaba GTE Reranker ModernBERT-base

Non-Reasoning

Kimi K3

Reasoning

Weight access

Alibaba GTE Reranker ModernBERT-base

Open Weight

Kimi K3

Pending

License

Alibaba GTE Reranker ModernBERT-base

Open Weight

Kimi K3

Pending

Release date

Alibaba GTE Reranker ModernBERT-base

Not sourced

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
A complete documented context comparison is not available.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Alibaba GTE Reranker ModernBERT-base 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, Alibaba GTE Reranker ModernBERT-base or Kimi K3?

Alibaba GTE Reranker ModernBERT-base is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Alibaba GTE Reranker ModernBERT-base or Kimi K3?

Alibaba GTE Reranker ModernBERT-base is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Alibaba GTE Reranker ModernBERT-base 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, Alibaba GTE Reranker ModernBERT-base or Kimi K3?

A complete documented context-window comparison is not available.

Benchmark evidence

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

Browse raw public benchmark evidence50 rows

Agentic

  • Terminal-Bench 2.1

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K388.3%
    Source

    Not directly comparable

  • BrowseComp

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K391.2%
    Source

    Not directly comparable

  • DeepSearchQA

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K395.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K373.2%
    Source

    Not directly comparable

  • MCP Atlas

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K384.2%
    Source

    Not directly comparable

  • AutomationBench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K330.8%
    Source

    Not directly comparable

  • JobBench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K352.9%
    Source

    Not directly comparable

  • APEX-Agents

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K337.6%
    Source

    Not directly comparable

  • SpreadsheetBench 2

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K334.8%
    Source

    Not directly comparable

  • DECK-Bench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K373.5%
    Source

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K380.9%
    Source

    Not directly comparable

  • ApprenticeBench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K318%
    Source

    Not directly comparable

Coding

  • DeepSWE

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K367.5%
    Source

    Not directly comparable

  • cursorBench32

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K360.8%
    Source

    Not directly comparable

  • FrontierSWE

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K381.2%
    Source

    Not directly comparable

  • ProgramBench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K377.8%
    Source

    Not directly comparable

  • Kimi Code Bench v2

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K372.9%
    Source

    Not directly comparable

  • sweMarathon

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K342%
    Source

    Not directly comparable

  • PostTrain Bench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K336.6%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K348.3%
    Source

    Not directly comparable

  • VulcanBench v3

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K373.7%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K357.3%
    Source

    Not directly comparable

  • FrontierSWE v2

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K325.9%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K387.2%
    Source

    Not directly comparable

  • SWE-bench (Vals)

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K393.4%
    Source

    Not directly comparable

  • PostTrainBench v1.1

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K332.0%
    Source

    Not directly comparable

Reasoning

  • JevBench 1.4

    Alibaba GTE Reranker ModernBERT-base0.15
    Source
    Kimi K3—

    Not directly comparable

  • JevBench 1.5

    Alibaba GTE Reranker ModernBERT-base0.00
    Source
    Kimi K3—

    Not directly comparable

  • ARC-AGI-1

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K394.50%
    Source

    Not directly comparable

  • ARC-AGI-2

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K360.4%
    Source

    Not directly comparable

Multimodal

  • OfficeQA Pro

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K363.3%
    Source

    Not directly comparable

  • MMMU-Pro

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K381.6%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K383.4%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K384.8%
    Source

    Not directly comparable

  • CharXiv

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K391.3%
    Source

    Not directly comparable

  • MathVision

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K394.3%
    Source

    Not directly comparable

  • MathVision w/ Python

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K397.8%
    Source

    Not directly comparable

  • BabyVision w/ Python

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K385.7%
    Source

    Not directly comparable

  • ZeroBench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K323.0%
    Source

    Not directly comparable

  • ZeroBench w/ Python

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K341.0%
    Source

    Not directly comparable

  • WorldVQA ForceAnswer

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K351.0%
    Source

    Not directly comparable

  • OmniDocBench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K391.1%
    Source

    Not directly comparable

  • PerceptionBench

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K358.5%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K393.5%
    Source

    Not directly comparable

  • GPQA-D

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K393.5%
    Source

    Not directly comparable

  • HLE

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K356%
    Source

    Not directly comparable

  • HLE w/o tools

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K343.5%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K392.9%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K388.0%
    Source

    Not directly comparable

Instruction following

  • Gray Swan IPI (15 attempts)

    Alibaba GTE Reranker ModernBERT-base—
    Kimi K352.7%
    Source

    Not directly comparable

50 public results · 0 shared

Watch Alibaba GTE Reranker ModernBERT-base 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.

Last updated September 30, 2026