Skip to content
LMC Feed-Models, Papers, Benchmarks. Zero Fluff.Live

Best AI Models for Roo Code

IDE Extension

Roo Code is a VS Code extension for AI-assisted development with multiple modes. It supports various models and benefits from strong code generation and instruction following.

Last updated: 22m ago
#1
Gemini 3.5 Flash
Google
Tool Score
86
Output $/M
$9.00
Arena Elo
1477
#2
Claude Opus 5.5
Anthropic
Tool Score
85
Output $/M
$20.00
#3
Claude Fable 5.1
Anthropic
Tool Score
85
Output $/M
$50.00

What Matters for Roo Code

Function CallingStreamingJSON ModeLarge ContextStrong Coding

Best Models for Roo Code

Top 15 by tool-optimized score

LMMarketCap.com

All Models Ranked for Roo Code (439 models)

Scored by: benchmark performance (90%) from MMLU, GPQA, HumanEval, SWE-bench, and 15+ standardized evaluations, with capabilities and context as tiebreakers (10%).

#ModelScoreOutput $/M
1Gemini 3.5 Flash
Arena Elo: 1477
86$9.00
2Claude Opus 5.585$20.00
3Claude Fable 5.185$50.00
4Claude Fable 5.1 (batch)85$25.00
5Claude Opus 585$25.00
6Claude Fable 5
SWE-bench: 95%
85$50.00
7Claude Fable 5 (batch)85$25.00
8GPT-5.5 Pro (batch)84$90.00
9Gemini 3.1 Pro Preview Custom Tools84$12.00
10Gemini 3.1 Pro Preview (batch)84$6.00
11GPT-5.4 Pro83$180.00
12GPT-5.4 Pro (batch)83$90.00
13GPT-5.3-Codex83$14.00
14GPT-5.2-Codex83$14.00
15GPT-5.2 Pro83$168.00
16GPT-5.2 Pro (batch)83$84.00
17Grok 4.782$6.00
18Grok 4.7 (batch)82$4.80
19Grok 4.682$6.00
20Grok 4.6 (batch)82$4.80
21GPT-5.6 Luna Pro82$1.20
22GPT-5.6 Luna Pro (batch)82$0.600
23GPT-5.6 Luna82$1.20
24GPT-5.6 Luna (batch)82$0.600
25GPT-5.6 Terra Pro82$12.00
26GPT-5.6 Terra Pro (batch)82$6.00
27GPT-5.6 Terra82$12.00
28GPT-5.6 Terra (batch)82$6.00
29GPT-5.6 Sol Pro82$20.00
30GPT-5.6 Sol Pro (batch)82$10.00
31GPT-5.6 Sol82$20.00
32GPT-5.6 Sol (batch)82$10.00
33Grok 4.582$6.00
34Claude Opus 4.8
SWE-bench: 88.6%
82$25.00
35Grok 4.382$2.50
36Grok 4.3 (batch)82$2.00
37GPT-5.5 Pro
SWE-bench: 88.7%
82$180.00
38GPT-5.5
SWE-bench: 88.7%
82$30.00
39GPT-5.5 (batch)82$15.00
40Grok 4.2082$2.50
41GPT-5.4 (batch)82$7.50
42Gemini 3 Flash Preview (batch)82$1.50
43GPT-5.2 (batch)82$7.00
44GPT-5.1-Codex-Max82$10.00
45GPT-5.1 (batch)82$5.00
46GPT-5.1-Codex82$10.00
47GPT-5.1-Codex-Mini82$2.00
48Claude Haiku 4.5
HumanEval: 89.8%
82$5.00
49GPT-5 Pro82$120.00
50GPT-5 Pro (batch)82$60.00

More Tool Rankings

CursorClaude CodeWindsurfGitHub CopilotAiderClineOpen WebUIWarpContinueZedLovable
Best for Coding Best for Reasoning Compare Models
Frequently Asked Questions

Based on our analysis of coding benchmarks, capability matching, and pricing, Gemini 3.5 Flash currently ranks #1 for Roo Code. Rankings are rebuilt as benchmark, pricing, and provider data refresh.

We score models using benchmark performance (90%) from LMArena, HumanEval, SWE-bench, MMLU, and 15+ standardized evaluations. Capabilities and context serve as tiebreakers (10%). Only models with the capabilities Roo Code needs are included in the tool-specific rankings.

We currently track 439 AI models compatible with Roo Code. This includes models from OpenAI, Anthropic, Google, DeepSeek, and other providers accessible via API.

Many open-source models are compatible with Roo Code through API providers like OpenRouter, Together AI, and Groq. Check our rankings to see which open-source models perform best.

Rankings refresh whenever the underlying benchmark, pricing, and catalog sources refresh. That means some signals update faster than others, and the page reflects the latest verified source data available.

Best AI Models for Roo Code - 2026 Rankings | LM Market Cap