by KimiCoding AgentfreemiumRank #5 on Leaderboard

Kimi Code CLI

Coding agent harness from Kimi, measured on the Artificial Analysis Coding Agent Index.

Overall Index
48.6/ 100
Artificial Analysis benchmark composite
SWE-bench Verified
—
Real-world GitHub issue resolution
FrontierCode-AA 2.0
22.0%
Multi-file software engineering tasks
Terminal-Bench 4.1
67.2%
Shell execution & command accuracy
Avg Cost / Task
$2.94
Inference token expenditure per task

Overview & Analysis

Kimi Code CLI was evaluated by Artificial Analysis with Kimi K3.1 Pro. We have not written a full profile for it yet.

Pricing Model: See the vendor for current pricing.

Technical Specs & Models

Primary EngineKimi K3.1 Pro
EnvironmentNot recorded
Platforms
LicenseNot recorded
Custom API Keys (BYOK)Bundled Only (No)
Supported Foundation Models:
Kimi K3.1 Pro

Key Capabilities & Features

Specialized engineering mechanisms implemented in Kimi Code CLI.

Pros & Cons Evaluation

Forensic analysis of developer experience, cost efficiency, and trade-offs.

Strengths & Advantages
    Limitations & Trade-Offs

      Pricing Plans & Tiers

      Subscription plans, credit quotas, and commercial deployment options.

      Verified Benchmark Evaluations

      Standardized evaluation scores recorded on SWE-bench and synthetic code harnesses.

      Benchmark HarnessScore / AccuracyEvaluation MetricVerification StatusEvaluation Notes
      Coding Agent Index (v2.1)48.6%Composite of three benchmarksVerifiedSource: Artificial Analysis.
      FrontierCode-AA 2.022%Software engineering tasksVerifiedStandard benchmark instance run.
      Terminal-Bench 4.167.2%Agentic terminal useVerifiedStandard benchmark instance run.
      SWE-Atlas-QnA-AA56.7%Technical Q&AVerifiedStandard benchmark instance run.