AiRecMark/AI Tools/Coding Agents/CodeGeeX (Zhipu AI)
RANK #47 IN CODING AGENTS

CodeGeeX

verified v2026.9 Coverage Tier

Zhipu AI multilingual code generation plugin

VENDOR: Zhipu AI • LICENSE: Proprietary / SaaS • SECURITY: Standard cloud security • LAST BENCHMARK: Verified 2026-09-16
Launch CodeGeeX arrow_forward
Empirical Performance Audit

Macro Intelligence Index

77.1 /100 Coverage Tier
Relative Velocity
#47 of 55
77.1/100 composite
Archive record
4 recorded features
Source: codegeex.cn
Output quality
score.dims.quality
source: archive
Output Quality & Reliability (Weighted 25%) 76.0%
correctness and consistency of primary task output. AiRecMark rubric v2
Feature Depth & Integrations (Weighted 20%) 74.0%
breadth of integrations, APIs, and advanced capabilities. AiRecMark rubric v2
Onboarding & Usability (Weighted 15%) 78.0%
onboarding friction, UI clarity, and workflow ergonomics. AiRecMark rubric v2
Runtime Performance & Latency (Weighted 20%) 76.0%
latency, throughput, and stability under load. AiRecMark rubric v2
Price-to-Value Efficiency (Weighted 20%) 82.0%
capability delivered per pricing tier dollar. AiRecMark rubric v2
Low-Level Verification

Quantitative Technical Specification

ISO/IEC 25010 Ref
terminal Runtime & Core Shell
Multi-file agentic edits

Core capability: multi-file agentic edits.

Source: CodeGeeX · Verified 2026-09-16
hub Context Indexing Engine
Repository-aware context indexing

Core capability: repository-aware context indexing.

Source: CodeGeeX · Verified 2026-09-16
device_hub Protocol Specification
IDE / CLI integration

Core capability: IDE / CLI integration.

Source: CodeGeeX · Verified 2026-09-16
smart_toy Model Agility & Routing
Official T0 source

Pricing and feature claims sourced from codegeex.cn.

Source: CodeGeeX · Verified 2026-09-16
Market Positioning Matrix

Direct Competitor Radar & Alternatives

Open Full Matrix open_in_new
Tool & Version Score Primary Sweet Spot Entry Pricing Action
C
CodeGeeX (Current)
77.1 Multi-file agentic edits Free tier Selected
CU
Cursor
94.2 Forked VS Code Agent $20/user/mo Compare vs
WI
Windsurf
91.8 Realtime Collaborative IDE Free / $15 Pro Compare vs
GI
GitHub Copilot
88.1 Enterprise Compliance $10/mo Compare vs
CL
Claude Code
86.1 Terminal & CI/CD Pipelines $17/mo Compare vs
Institutional Synthesis

Analyst Consensus Verdict

“CodeGeeX stands out for purpose-built for multilingual code generation. Zhipu AI multilingual code generation plugin anchors its proposition, and AiRecMark's five-dimension audit lands it at 77.1/100 — a pragmatic default for multilingual Code Generation.”
— AiRecMark Senior Systems Architecture Committee
verified Verified Strategic Strengths
  • ✓ Purpose-built for multilingual: code generation
  • ✓ Multi-file agentic edits: out of the box
  • ✓ T0 pricing and: features verified against the official site
  • ✓ Best Fit: Multilingual Code Generation
warning Institutional Trade-offs & Headwinds
  • ! Public-info editorial assessment: (not full hands-on testing)
  • ! No verifiable third-party: benchmark published
  • ! :
  • ! Scope: Editorial assessment based on public information; hands-on retest pending.
Total Cost of Ownership

Commercial Tiers

Transparent
Free $0 forever

Entry tier for evaluation and light individual use.

Entry evaluation tier
Most Deployed
Pro Custom

Free tier · paid plans available

Verified 2026-09-16 · codegeex.cn
Enterprise Custom

Dedicated infrastructure, security review, and compliance support.

SSO / SAML & audit controls
TCO MODEL NOTE: Official pricing: Free tier · paid plans available. Verified via codegeex.cn (2026-09-16); overages and enterprise terms bill per the official pricing page.
Archive Record

Recorded Metadata

ARCHIVE SNAPSHOT snapshot 2026-09-16
OFFICIAL SOURCE Source: codegeex.cn
PRICING CHECKED Snapshot 2026-09-16
SCORING MODEL v2-5dim
RECORDED FEATURES AiRecMark Editorial
Category Standing

Ecosystem Gravity

Category Rank #47 of 55
Best For Best for: Multilingual Code Generation
Sources: Official docs, codegeex.cn, community signals N=4 recorded attributes
shield_with_heart AIRECMARK EMPIRICAL PROTOCOL v2.4 • Independent, un-sponsored deterministic evaluation clusters.
All benchmarks executed in sandboxed hypervisors with standardized token latency meters.