WritingmateWritingmate

AI model reference · 2026

Kimi K3

MoonshotAI: Kimi K3 logoMoonshot AIModel details, evidence, and API facts

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

Text generation
Image input
Reasoning
Provider endpoint accepts tool parameters
Try Kimi K3Compare with another model
Context window
1,048,576 tokens
Maximum output
Not available
Base provider API input
$3.00 / 1M tokens
Base provider API rate
Published evidence
5 benchmarks, 0 Arena results

Overview

About Kimi K3

A concise catalog overview. Technical limits and published evaluation evidence are listed separately below.

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

text
multimodal
reasoning

Published evaluations

Benchmark results

Only results mapped to this exact model and backed by a named source appear here. Different evaluation protocols are not treated as interchangeable.

Source-backed benchmark results for Kimi K3
BenchmarkScoreEvaluation detailsSource
AutomationBench-AAA 657-task benchmark of multi-step work across simulated SaaS applications in six business domains. The Artificial Analysis protocol reports a guardrail-aware score and is distinct from both the public Zapier split and the unrelated dynamic AutoBench framework.52.7%Guardrail-aware scoreVersion: AutomationBench-AA 2026 · Split: 657 tasks across Finance, HR, Marketing, Operations, Sales, and Support · Harness: Artificial Analysis independent implementation · Attempts: One evaluated run per task · Tools: REST APIs for simulated SaaS applications · Evaluator: Programmatic end-state grader with guardrail checks · Reasoning effort: maxMethodology Artificial AnalysisIndependently reproduced
DeepSWE 1.1A long-horizon software-engineering benchmark with 113 original tasks graded by hand-written tests.69.0%±5Pass@1Version: DeepSWE 1.1 · Split: 113 tasks across 91 repositories · Harness: mini-swe-agent · Reasoning effort: maxProtocol note: All models use the same harness. Cost, output-token, and step counts are retained per result as protocol context.; Confidence interval: ±5Methodology DataCurveBenchmark owner
GPQA DiamondThe highest-quality subset of Graduate-Level Google-Proof Q&A, designed to test expert-level scientific reasoning in biology, physics, and chemistry.93.5%AccuracyVersion: GPQA Diamond 198 · Split: 198 Diamond questions · Harness: Artificial Analysis independent evaluation · Tools: Not disclosed on the score page · Reasoning effort: maxMethodology Artificial AnalysisIndependently reproduced
Humanity's Last ExamA 2,500-question expert-level benchmark spanning dozens of academic fields. Tool-assisted and no-tools results are separate protocols and must not be merged.46.9%AccuracyVersion: May 2025 text-only revision · Split: 2,158 text-only questions from the 2,500-question May 2025 revision · Attempts: pass@1 · Tools: No browser or retrieval tools · Evaluator: LLM equality checker with numerical tolerance · Reasoning effort: maxMethodology Artificial AnalysisIndependently reproduced
LiveBenchA contamination-resistant benchmark refreshed on a fixed release cadence. Scores from different LiveBench releases must never be compared as the same protocol.79.2%Mean of category averagesVersion: LiveBench 2026-06-25 · Split: 2026-06-25 release, 23 tasks across seven categoriesProtocol note: Overall is the mean of category averages. This protocol is not comparable with the 2026-01-08 release.Methodology LiveBenchBenchmark owner

Human preference

Arena results

Arena scores come from blind human preference votes. They are reported separately from task benchmarks and are not used as substitutes for missing benchmark results.

No exact Arena match is available for this model. Similar names and provider variants are not merged automatically.

Technical reference

Specifications and API facts

Technical limits and reference provider prices come from the current catalog unless a reviewed external source is listed. Missing values stay marked as unavailable.

Model
Provider
Moonshot AI
Release date
Not available in reviewed sources
Catalog added
Jul 16, 2026
Context window
1,048,576 tokens
Maximum output
Not available
Knowledge cutoff
Not available in reviewed sources
License
Not available in reviewed sources
Capabilities and API
Input types
Text, Image, Video
Output types
Text
Reasoning
Supported
Provider endpoint tool parameters
Accepts tool parameters
Base provider API input
$3.00 / 1M tokens
Base provider cached input
$0.30 / 1M tokens
Base provider API output
$15 / 1M tokens

These are reference provider API rates, not Writingmate checkout charges. Access in Writingmate follows the allowances of your Writingmate plan.

Provenance

Sources and update status

Source links are attached to the facts and evaluations they support. Catalog-only values are not presented as independently verified claims.

Evidence last updated Aug 9, 2026.

Catalog record updated Jul 16, 2026.

Catalog-added dates describe when a model entered the catalog, not necessarily its public release date.

Try Kimi K3 in Writingmate

Use this model, then compare its response with other AI models in the same workspace.

Get startedCompare models