AICODA
Updated JUN 8, 2026
Compare real value

Find the AI coding subscription that delivers real value.

We evaluate 10 plans and 16 models across real-world coding benchmarks, usage limits, and reliability so you can choose with confidence.

10
Plans
16
Models
6
Benchmarks
Updated
JUN 8, 2026
profile
Z.ai

GLM Coding Plan

GLM-5.1
59.3 value index
value
59.3 /100
coding
59.3 /100
reliability
73.5 /100
$10/mo · Lite

Strong value performance makes GLM Coding Plan the current top pick.

DeepSeek

DeepSeek API

DeepSeek V4 Pro
51.2 value index
value
51.2 /100
coding
61.2 /100
reliability
70.4 /100
$16/mo · pay-per-token

DeepSeek API stays close with balanced scores and credible coding depth.

Pay-per-token only — no subscription. Cost shown scales with the selected usage profile; default prefix caching cuts repeat-input cost up to ~100×.
Moonshot AI

Kimi Membership + Kimi Code

Kimi K2.6
47.6 value index
value
47.6 /100
coding
60.9 /100
reliability
66.7 /100
$19/mo · Moderato

Competitive pricing and steady day-to-day performance keep Kimi Membership + Kimi Code in the top three.

All plans 10 plans

Plan
Z
GLM Coding Plan
GLM-5.1
$10
Lite
59.3 3/6
59.3
73.5
203K57.9 t/sOPEN
DS
DeepSeek API
DeepSeek V4 Pro
$16
pay-per-token
61.2 3/6
51.2
70.4
1M53.2 t/sOPEN
K
Kimi Membership + Kimi Code
Kimi K2.6
$19
Moderato
60.9 3/6
47.6
66.7
262K44.1 t/sOPEN
CU
Cursor Pro
Cursor Composer 2.5
$20
Pro
61.2 1/6
47.0
60.0
200K
M
MiniMax Token Plan
MiniMax M3
$20
Plus
60.4 1/6
46.4
67.6
1.05M38.8 t/sOPEN
x
SuperGrok + Grok Build
Grok 4.3
$30
SuperGrok
59.8 1/6
40.5
63.9
1M186.9 t/s
ChatGPT Pro + Codex
GPT-5.5
$100
Pro 5x
68.7 6/6
34.4
74.4
1.05M63.4 t/s
AI
Claude Max
Claude Opus 4.7
$100
Max 5x
67.7 6/6
33.9
75.7
1M
Q
Qwen Coding Plan
Qwen3.6-27B
$50
Pro
57.1 3/6
33.6
62.0
OPEN
G
Google AI + Antigravity
Gemini 3.1 Pro
$100
AI Ultra 5x
63.7 4/6
31.9
72.7
1M139.8 t/s

Scoring combines benchmark performance, real-world task success, usage limits, and price into Coding, Value, and Reliability (0–100).

Learn our methodology →

Methodology

Coding score

Difficulty-centered composite: each result counts as its deviation from that benchmark’s observed average, so being measured on a hard benchmark doesn’t hurt and a generously-scored one doesn’t inflate. Deviations are weighted over the full benchmark set — a missing benchmark counts at its average, so sparse coverage dilutes toward the mean — and anchored to the dataset average. The basis (e.g. “3/6”) shows coverage only, not the denominator. Self-reported results count at 75% of their deviation. Independent benchmarks weigh more than vendor-run ones:

  • SWE-bench Verified ×1 mixed
  • GSO ×1 independent
  • Terminal-Bench 2.0 ×1.5 independent
  • DeepSWE ×1.5 independent
  • AA Coding Index ×1.5 independent
  • CursorBench ×0.5 vendor-self-reported

Value index

coding score ÷ log₁₀(effective cost), where effective cost is the cheapest tier whose estimated monthly quota covers your usage profile. Costs are floored at $10 so near-free API pricing can’t dominate the index. API-only cost assumes 80% input / 20% output tokens.

  • Light 5M tokens/mo
  • Daily 30M tokens/mo
  • Heavy 150M tokens/mo

Vendors express quotas in incompatible units (prompts per 5h, weekly hours, credits) — each tier carries its conversion assumption verbatim in the expanded row, and each plan a quota-confidence label (high/medium/low) for how solid the vendor’s published numbers are. The label never changes a score. Treat estimates as directional, not exact.

Reliability

70% curated editorial judgment per provider (incident/degradation history, quota pain, limit transparency — rationale in the expanded row) + 30% measured behavior of the shown model, the mean of three independent Artificial Analysis evals: non-hallucination rate (AA-Omniscience — admitting ignorance instead of confabulating), IFBench (instruction following) and τ²-Bench (agentic tool-calling dependability).

Every price, quota and benchmark entry links its source and carries a verification date. Data last verified Jun 8, 2026. Prices in USD as quoted by vendors; quarterly/annual plans converted to effective monthly.

© 2026 AICODA

All scores are our evaluation and may change.

Questions or feedback? hello@aicoda.dev