AI model equivalents

AI model equivalents: the Opus, Sonnet and Haiku of every coding CLI

You know the Claude lineup by heart, then you open Codex, Gemini or Grok and none of the names tell you which model plays the role of Opus. This page places every model of every coding agent CLI AgentsRoom runs on one scale, so each one reads in terms you already know.

Read live from the AgentsRoom model catalogue. Popularity as of Nov 20, 2026, 7:48 PM.

CLIs compared

19

Models placed

231

Launches counted, last 30 days

215,051

The short answer

Claude is the yardstick because it is the lineup most developers know. Each line names the models of other vendors that play the same role today.

Fable class

Fable-class (frontier) equivalents

The frontier models, one step above Opus: GPT-6.2 Astra in Codex, Daybreak Blue in Codex, and GPT-5.6 Sol Max in Codex.

For the hardest problems, at the highest price.

Opus class

Opus equivalents

The models that play the role of Claude Opus: GPT-6.2 Sol in Codex, Gemini 3.1 Pro (High) in Antigravity, Grok 4.7 in Grok, DeepSeek V4 Pro (latest) in Command Code, Kimi K3 in Command Code, GLM-5.3 in Command Code, Qwen 3.8 Max Prime in Command Code, and Gemini 3.8 Flash in Command Code.

The flagship most serious coding work runs on.

Sonnet class

Sonnet equivalents

The models that play the role of Claude Sonnet: GPT-6.1 Terra in Codex, GPT-6 Luna in Codex, Gemini 3.8 Flash (High) in Antigravity, GLM 5.3 in OpenCode, Qwen3.8 Max in OpenCode, Kimi K3.1 Pro in Kimi, DeepSeek V4 Pro in Pi, and Medium 3.5 in Mistral Vibe.

Balanced: strong enough for most features, cheaper than the flagship.

Haiku class

Haiku equivalents

The models that play the role of Claude Haiku: Codex Spark in Codex, DeepSeek V4 Flash in oh-my-pi, Qwen3 Coder in Ollama, GLM 4.6 in Ollama, and Gemini 3.5 Flash Lite in Command Code.

Light and fast: renames, small fixes, summaries.

Every coding CLI, tier by tier

One row per CLI AgentsRoom runs, one column per tier. Current models come first; the older versions a list still offers are counted under them.

AI model equivalents by coding agent CLI and capability tier
CLIFrontierFable classOpus classSonnet classHaiku class
Claude
FableFable 5.2
OpusOpus 5.5
+2 older versions

Opus 5, Opus 4.8

SonnetSonnet 5.5
+1 older version

Sonnet 5

Haiku
Codex
GPT-6.2 AstraDaybreak BlueDaybreak RedGPT-5.6 Sol Max
+1 older version

GPT-6 Astra

GPT-6.2 Sol
+4 older versions

GPT-6.1 Sol, GPT-6 Sol, GPT-5.6 Sol, GPT-5.5

GPT-6.1 TerraGPT-6 Luna
+4 older versions

GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.4, GPT-5.2

Codex Spark
+1 older version

GPT-5.4 Mini

AntigravityNone
Gemini 4 Argon (Low)Gemini 4 Argon (Medium)Gemini 4 Argon (High)Gemini 4 Carbon (Low)Gemini 4 Carbon (Medium)Gemini 4 Carbon (High)Gemini 4 Hydrogen (Low)Gemini 4 Hydrogen (Medium)Gemini 4 Hydrogen (High)Gemini 4 Hydrogen (XHigh)Gemini 4 Neon (Low)Gemini 4 Neon (Medium)Gemini 4 Neon (High)Gemini 4 Neon (XHigh)Gemini 3.1 Pro (High)Claude Opus 5.5 (High)Claude Opus 5.5 (Medium)
Gemini 3.8 Flash (High)Gemini 3.8 Flash (Medium)Claude Sonnet 5.5 (High)Claude Sonnet 5.5 (Medium)
+5 older versions

Gemini 3.7 Flash (High), Gemini 3.7 Flash (Medium), Gemini 3.6 Flash (High), Gemini 3.6 Flash (Medium), Gemini 3.5 Flash (Medium)

None
OpenCodeNone
GPT-5.5Claude Opus
Claude SonnetKimi K3GLM 5.3Qwen3.8 Max
None
GrokNone
Grok 4.7
NoneNone
GitHub Copilot
GPT-6 Astra
GPT-6.1 SolClaude Opus 5.5GPT-5.5Gemini 4 Argon
+4 older versions

GPT-6 Sol, Claude Opus 5, GPT-5.6 Sol, Claude Opus 4.8

Claude Sonnet 5.5GPT-6 LunaGPT-5.6 TerraGemini 3.7 FlashKimi K3
+3 older versions

Claude Sonnet 5, GPT-5.6 Luna, Claude Sonnet 4.6

Claude Haiku 5.5MAI-Code-1.1-Flash
+1 older version

Claude Haiku 4.5

oh-my-piNone
Claude Opus 5.5GPT-6 Sol
Claude Sonnet 5Gemini FlashGLM 5.3
+1 older version

GLM 5.2

DeepSeek V4 Flash
OllamaNoneNone
Qwen3 Coder 480B
Gemma 3Qwen3 CoderGLM 4.6
KimiNoneNone
Kimi K3.1 ProKimi K3.1 Pro HighSpeedKimi K3Kimi K3-256KKimi K2.8 PreviewK2.7 Code HighSpeed
None
PiNone
Claude Opus 5.5GPT-6 Sol
Claude Sonnet 5Gemini FlashGLM 5.3DeepSeek V4 Pro
+1 older version

GLM 5.2

None
DevinNone
Claude OpusGPTCodexGemini
SWEClaude SonnetGLMKimiDeepSeek
Claude Haiku
Mistral VibeNoneNone
Medium 3.5
None
Command Code
Claude Fable 5.1Claude Fable 5GPT-6 AstraGemini 4 Argon
DeepSeek V4 Pro (latest)Kimi K3GLM-5.3MiMo V2.6 ProMiMo V2.6 Pro UltraSpeedQwen 3.8 Max PrimeQwen 3.8 Max 0902Qwen 3.8 MaxStep 5 PreviewTencent Hy4 PreviewLing 3.1 FlashClaude Opus 5.5Claude Opus 5GPT-6.1 SolGPT-5.5Gemini 3.8 FlashFugu UltraMuse Spark 1.3Muse Spark 1.3 ContributorMuse WonderGrok 4.7
+5 older versions

Claude Opus 4.8, Claude Opus 4.7, GPT-6 Sol, GPT-5.6 Sol, Grok 4.6

DeepSeek V4 Flash Vision (exp)DeepSeek V4.1 FlashDeepSeek V4.1 Flash FastKimi K3.1 ProKimi K2.7 CodeKimi K2.7 Code HighSpeedGLM-5.3 FlashGLM-5.3 FlashXGLM-5.2 FastMiniMax M3.1 FlashMiniMax M3.1 Flash FreeMiniMax M3MiMo V2.6 FlashQwen 3.8 27BQwen 3.8 FlashQwen 3.6 Max PreviewTencent Hy3Nemotron 3.5 Super VLInklingInkling SmallMistral Large 4Claude Sonnet 5.5Claude Sonnet 5GPT-6 LunaGPT-5.6 TerraGPT-5.3 CodexMuse Spark Open
+21 older versions

DeepSeek V4 Flash (latest), DeepSeek V4 Flash Fast, Kimi K2.6, Kimi K2.5, GLM-5.2, GLM-5.1, GLM-5, MiniMax M2.7, MiniMax M2.5, MiMo V2.5 Pro, Qwen 3.7 Max, Claude Sonnet 4.6, GPT-5.6 Luna, GPT-5.4, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash, Muse Spark 1.1, Muse Spark 1.2, Muse Spark 1.2 Contributor, Grok 4.5

MiMo V2.5Qwen 3.8 Omni FlashQwen 3.7 PlusLongCat 2.0Step 3.7 FlashNemotron 3 UltraClaude Haiku 5.5GPT-5.4 MiniGemini 3.5 Flash Lite
+4 older versions

Qwen 3.7 Flash, Qwen 3.6 Plus, Claude Haiku 4.5, Gemini 3.1 Flash Lite

Muse CodeNone
Muse Spark 1.3Muse WonderMuse Wonder Full
Muse Ember
+1 older version

Muse Spark 1.2

None
AiderNone
Claude Opus
Claude SonnetDeepSeek
GPT-4o
MiniMax CodeNone
MiniMax M3
MiniMax M3.1 Flash
None
ZCodeNone
GLM-5.3GLM-5.3GLM-5.3
GLM-5.3 FlashGLM-5.3 FlashGLM-5.3 Flash
None
Qwen CodeNoneNone
Qwen3.8 Max
+1 older version

Qwen3.7 Max

Qwen3.7 PlusQwen3 Coder PlusQwen3 Coder Next
KiroNone
Claude Opus 4.8
Claude Sonnet 4.6
None
FreebuffPicks the model for you on every request: no fixed tier.
CursorPicks the model for you on every request: no fixed tier.
AmpPicks the model for you on every request: no fixed tier.
Hermes AgentPicks the model for you on every request: no fixed tier.
GoosePicks the model for you on every request: no fixed tier.
Rovo DevPicks the model for you on every request: no fixed tier.
  • Among the three models of its CLI the community launches most
  • Older version: a newer generation of the same model is in the same list

Same model, several CLIs

A model family is not tied to its vendor's tool. Here is every family that more than one CLI ships today, with the name each CLI gives it.

Claude Opus

Opus class

10 CLIs

  • ClaudeOpus 5.5
  • AntigravityClaude Opus 5.5 (High)
  • OpenCodeClaude Opus
  • GitHub CopilotClaude Opus 5.5
  • oh-my-piClaude Opus 5.5
  • PiClaude Opus 5.5
  • DevinClaude Opus
  • Command CodeClaude Opus 5.5
  • AiderClaude Opus
  • KiroClaude Opus 4.8

Claude Sonnet

Sonnet class

10 CLIs

  • ClaudeSonnet 5.5
  • AntigravityClaude Sonnet 5.5 (High)
  • OpenCodeClaude Sonnet
  • GitHub CopilotClaude Sonnet 5.5
  • oh-my-piClaude Sonnet 5
  • PiClaude Sonnet 5
  • DevinClaude Sonnet
  • Command CodeClaude Sonnet 5.5
  • AiderClaude Sonnet
  • KiroClaude Sonnet 4.6

GLM

7 CLIs

  • OpenCodeGLM 5.3
  • oh-my-piGLM 5.3
  • OllamaGLM 4.6
  • PiGLM 5.3
  • DevinGLM
  • Command CodeGLM-5.3 Flash
  • ZCodeGLM-5.3

GPT Sol

Opus class

5 CLIs

  • CodexGPT-6.2 Sol
  • GitHub CopilotGPT-6.1 Sol
  • oh-my-piGPT-6 Sol
  • PiGPT-6 Sol
  • Command CodeGPT-6.1 Sol

Gemini Flash

5 CLIs

  • AntigravityGemini 3.8 Flash (High)
  • GitHub CopilotGemini 3.7 Flash
  • oh-my-piGemini Flash
  • PiGemini Flash
  • Command CodeGemini 3.8 Flash

Kimi

Sonnet class

5 CLIs

  • KimiKimi K3.1 Pro
  • OpenCodeKimi K3
  • GitHub CopilotKimi K3
  • DevinKimi
  • Command CodeKimi K3.1 Pro

DeepSeek

5 CLIs

  • oh-my-piDeepSeek V4 Flash
  • PiDeepSeek V4 Pro
  • DevinDeepSeek
  • Command CodeDeepSeek V4.1 Flash
  • AiderDeepSeek

Claude Haiku

Haiku class

4 CLIs

  • ClaudeHaiku
  • GitHub CopilotClaude Haiku 5.5
  • DevinClaude Haiku
  • Command CodeClaude Haiku 5.5

Qwen

4 CLIs

  • OpenCodeQwen3.8 Max
  • OllamaQwen3 Coder
  • Command CodeQwen 3.8 Omni Flash
  • Qwen CodeQwen3.8 Max

GPT Astra

Fable class

3 CLIs

  • CodexGPT-6.2 Astra
  • GitHub CopilotGPT-6 Astra
  • Command CodeGPT-6 Astra

GPT Luna

Sonnet class

3 CLIs

  • CodexGPT-6 Luna
  • GitHub CopilotGPT-6 Luna
  • Command CodeGPT-6 Luna

GPT Terra

Sonnet class

3 CLIs

  • CodexGPT-6.1 Terra
  • GitHub CopilotGPT-5.6 Terra
  • Command CodeGPT-5.6 Terra

Claude Fable

Fable class

2 CLIs

  • ClaudeFable 5.2
  • Command CodeClaude Fable 5.1

Muse Spark

Opus class

2 CLIs

  • Muse CodeMuse Spark 1.3
  • Command CodeMuse Spark 1.3

Grok

Opus class

2 CLIs

  • GrokGrok 4.7
  • Command CodeGrok 4.7

Mistral

Sonnet class

2 CLIs

  • Mistral VibeMedium 3.5
  • Command CodeMistral Large 4

What developers actually launch

The most launched models of the last 30 days among AgentsRoom users, read in tier terms. Equivalents tell you which models play the same role; launches tell you which ones people pick.

  1. 1

    OpusOpus class

    Claude945 members

    27.6% of launches

  2. 2

    SonnetSonnet class

    Claude467 members

    13% of launches

  3. 3

    Opus 5.5Opus class

    Claude197 members

    10.4% of launches

  4. 4

    HaikuHaiku class

    Claude153 members

    10.2% of launches

  5. 5

    GPT-6.1 SolOpus class

    Codex306 members

    10% of launches

Full usage statistics, by CLI and by model

How the tiers are assigned

The four approximate tiers are anchored on Claude: Fable, Opus, Sonnet and Haiku. Reviewed models use an explicit catalogue tier; other entries retain the existing family-based fallback. These tiers are guides, not guarantees of equal results.

Command Code and Muse Code use published coding benchmarks for reviewed models. The word Spark alone does not mean a lightweight model: Muse Spark 1.3 is in Opus class, while Codex Spark remains in Haiku class.

Open weights do not impose a tier ceiling. A reviewed model can reach Opus class based on its coding results. Older catalogue entries may keep a different fallback until they are reviewed; the model name or its price alone does not establish an equivalence.

Routers get no tier, because they pick a model on each request: GitHub Copilot (Auto), Freebuff (Freebuff default), Cursor (Default), Devin (Adaptive), Amp (Amp default), Hermes Agent (Default), Goose (Default), Qwen Code (Default), Kiro (Default), and Rovo Dev (Default). Neither does a family the table does not know yet: no equivalence is better than a wrong one.

A tier is not a benchmark score. Two models of the same tier still differ in price, speed, context window, usage limits and the tasks they do best. Use the table to know where to look, then try both on your own task.

Data: the model catalogue AgentsRoom serves to its desktop and mobile apps, read at every visit, and the tier rules the app applies under every model list. Popularity: real agent launches from AgentsRoom desktops that have not declined usage sharing, over the last 30 days, refreshed every ten minutes.

Frequently asked questions

Ask us something else
Which Codex model is the equivalent of Claude Opus?
GPT-6.2 Sol. In the table above, Claude Opus and GPT-6.2 Sol both sit in the Opus class: the flagship most serious coding work runs on, one step below the frontier tier. Codex's frontier model, the counterpart of Fable, is GPT-6.2 Astra. For Sonnet-class work, the Codex model is GPT-6.1 Terra. And the Haiku-class model of the list is Codex Spark.
What is the Gemini equivalent of Claude Opus?
Gemini 3.1 Pro (High), through Antigravity, is currently placed in Opus class. The tier is an approximate comparison, not a guarantee of identical results on every task. For Sonnet-class work, the table currently lists Gemini 3.8 Flash (High).
Which GPT model is the equivalent of Claude Sonnet?
GPT-6.1 Terra, in Codex. OpenAI's balanced line sits in the Sonnet class: strong enough for most features, cheaper than the flagship.
What is the OpenAI equivalent of Claude Haiku?
Codex Spark, in Codex: the light, fast model of the lineup, for renames, small fixes and quick questions.
Is GPT-6.2 Sol as good as Opus 5.5?
GPT-6.2 Sol and Opus 5.5 share an approximate tier, but their results can differ with the task, version and reasoning effort. Price, speed, context and usage limits also matter. Compare them on the same task: AgentsRoom can run both side by side in one project.
What is the Gemini equivalent of Codex?
Antigravity CLI, started with the agy command. Codex is OpenAI's coding agent in the terminal, and Antigravity CLI plays that role at Google: Google moved individual users off Gemini CLI to it in June 2026, while Gemini CLI stays reachable with paid API keys. The comparison is ours, neither vendor publishes it. For the models themselves, read the table above.
Where can I use Claude Opus outside Claude Code?
Today, Opus is also in the model lists of Antigravity, OpenCode, GitHub Copilot, oh-my-pi, Pi, Devin, Command Code, Aider, and Kiro, under the name each CLI gives it. Same family, same tier: the equivalence does not change with the CLI that serves it.
Can an open-weight model be in Opus class?
Yes. Open weights do not limit capability. Reviewed tiers use coding benchmarks with their model versions and reasoning settings. The result is an approximation, not a claim that one model replaces Opus on every task. Entries without a reviewed tier keep the existing fallback.
Why do Auto and Default have no equivalent?
Because they are not a model: GitHub Copilot (Auto), Freebuff (Freebuff default), Cursor (Default), Devin (Adaptive), Amp (Amp default), Hermes Agent (Default), Goose (Default), Qwen Code (Default), Kiro (Default), and Rovo Dev (Default) let the service pick a model on each request, so there is no fixed capability to compare. The table leaves them out rather than guess.
How up to date is this table?
It is computed every time the page is opened, from the same model catalogue the AgentsRoom app serves to every desktop and phone. When AgentsRoom adds a model a CLI has released, it appears here at once, in its tier, and the version it replaces is marked older. The popularity flames are refreshed every ten minutes from the last 30 days of launches.
Can AgentsRoom pick the right model for my task?
Yes, in two ways, and both only suggest. AI Suggestion sizes the task before the session opens (Quick, Standard, Complex or Extreme) and opens the agent on the cheapest model of its CLI that can still do it. Adaptive Mode reads your draft once the CLI is running and suggests a lighter model when the task does not need the flagship, or tells you the current one is right.

In AgentsRoom

AgentsRoom answers this inside your model picker

AgentsRoom is a desktop command center for AI coding agents. Claude, Codex, GitHub Copilot CLI, Cursor and 20 other agent CLIs run side by side, each agent on the model you choose. The equivalences of this page are the ones the app shows you while you choose, and a few smart features help you size the model to the task.

≈ Opus under every model

Every model list (new agent, quick launch, backlog ticket, mobile app) tags each model with its counterpart in the CLI you know best, and sorts by power, price or popularity.

Model equivalents in the app

Let the task pick the model

AI Suggestion turns a one-line description into a complexity level (Quick, Standard, Complex, Extreme) and opens the agent on the cheapest model that fits. Adaptive Mode checks your draft and suggests a lighter model when the flagship is overkill.

AI Suggestion and Adaptive Mode

Overflow to the equivalent model

When an account nears its limit, a quota rule can start new agents on another CLI model by model: Fable, Opus and Sonnet each go to their counterpart of the same tier, pre-filled from these tiers.

Quota rules and usage alerts

The right model per ticket

Pin a provider, a model and a reasoning effort on a backlog ticket, so the agent that runs it uses exactly that, and keep the flagship for the tickets that need it.

Backlog task board

Hand the tests to a cheaper model

A developer agent on a flagship model hands the test run to a QA agent on a lighter one over MCP, so the expensive model stays on the code.

Agent delegation

A model per step

In an agent team, every step has its own role, CLI and model: the architect on a frontier model, the implementer on the Opus class, the reviewer wherever it pays off.

Agent teams
Download AgentsRoomFree

Further reading