Skip to content
IFAI

Model rankings

896 models · 5 boards · 2 sources

WebDev arena · People compare web pages built by two models · Published November 9, 2026

Best web builder
Claude Opus 5.5 (Max)Anthropic1,818Score
Best open model
Kimi K3.1 Pro (Max)Moonshot AI1,688Score
Best from China
Kimi K3.1 Pro (Max)Moonshot AI1,688Score
Most voted
GPT-6 Luna (Max)OpenAI29,989Votes
Top three by Score
1Claude Opus 5.5 (Max)Anthropic1,818
Top three open models
1Kimi K3.1 Pro (Max)Moonshot AI · #9 overall1,688
2DeepSeek-V4.1-Flash-20261017 (Max)DeepSeek · #14 overall1,664
3Kimi K3 (Max)Moonshot AI · #15 overall1,657
This week's changes
Simba 3.5Speech · #5New
Bach 1.0 ProVideo · #7New
RankChangeModelScore95% intervalVotesPrice $/M
1—Claude Opus 5.5 (Max)ClosedAnthropic1,818±124,009$8.0
2—Claude Sonnet 5.5 (xHigh)ClosedAnthropic · 1 more variant1,774±105,493$4.0
3—Gemini 4 Carbon (High)ClosedGoogle1,768±152,128$8.0
4—GPT-6 Astra (Max)ClosedOpenAI1,767±98,117$20
5—Claude Fable 5.1 (Max)ClosedAnthropic1,745±89,453$20
6—GPT-6.1 Sol (Max)ClosedOpenAI1,743±105,250$4.0
7—Muse Wonder Full (Max)ClosedMeta1,724±142,080—
8—Claude Opus 5 (Max)ClosedAnthropic · 1 more variant1,691±619,593$10
9—Gemini 4 Argon (High)ClosedGoogle1,683±104,626$8.0
10—GPT-6.1 Terra (Max)ClosedOpenAI1,679±113,559$2.0
11—GPT-6 Sol (Max)ClosedOpenAI1,674±96,882$4.0
12—Muse Spark 1.3 (Max)ClosedMeta · 1 more variant1,654±711,758$2.0
13—Muse Wonder (Max)ClosedMeta1,650±104,875$8.0
14—Inkling 2 SmallClosedThinking Machines1,649±20964$0.48
15—Grok 4.7 (xHigh)ClosedxAI1,639±87,816$3.0
16—Claude Fable 5 (High)ClosedAnthropic1,625±617,017—
17—Grok 4.6 (High)ClosedxAI1,618±712,193$3.0
18—GPT-5.6 Sol (xHigh, Codex Harness)ClosedOpenAI1,615±618,929—
19NewMuse Ember (Max)ClosedMeta1,608±171,345$0.20
20▼ 1Claude Haiku 5.5 (High)ClosedAnthropic1,595±96,174$0.20
21▼ 1Gemini 3.7 Flash (High)ClosedGoogle1,588±614,619—
22▼ 1Gemini 3.8 Flash (High)ClosedGoogle1,584±713,485$1.5
23▼ 1GPT-6 Luna (Max)ClosedOpenAI1,578±629,989$0.20
24▼ 1Claude Opus 4.7 (High)ClosedAnthropic · 1 more variant1,557±617,616—
25▼ 1Claude Opus 4.8 (High)ClosedAnthropic · 1 more variant1,555±618,061—
26▼ 1Grok 4.5ClosedxAI1,552±710,815—
27▼ 1Claude Opus 4.6 (High)ClosedAnthropic · 1 more variant1,546±619,080—
28▼ 1Muse Spark 1.1ClosedMeta1,542±87,850—
29▼ 1Claude Sonnet 5 (High)ClosedAnthropic1,539±616,802—
30▼ 1Gemini 3.6 Flash (High)ClosedGoogle1,538±88,538—
31▼ 1Muse Spark 1.2 (xHigh)ClosedMeta1,534±142,121—
32▼ 1Claude Sonnet 4.6ClosedAnthropic1,522±522,558—
33▼ 1GPT-5.6 Terra (xHigh, Codex Harness)ClosedOpenAI1,520±615,502$4.5
34▼ 1GPT-5.6 Luna (xHigh, Codex Harness)ClosedOpenAI1,519±612,231$0.45
35▼ 1GPT-5.5 (xHigh, Codex Harness)ClosedOpenAI · 2 more variants1,512±615,398—
36▼ 1Gemini 3.5 Flash (High)ClosedGoogle · 1 more variant1,500±79,167—
37▼ 1Claude Opus 4.5 (High, 32K, 20251101)ClosedAnthropic · 1 more variant1,493±810,930—
38▼ 1GPT-5.4 (High, Codex Harness)ClosedOpenAI · 2 more variants1,462±191,340—
39▼ 1Gemini 3.1 Pro PreviewClosedGoogle1,446±523,865—
40▼ 1Gemini 3 ProClosedGoogle1,441±813,937—
41▼ 1Gemini 3 FlashClosedGoogle · 1 more variant1,440±910,793—
42▼ 1Gemini 3.5 Flash-LiteClosedGoogle1,435±41233$0.85
43▼ 1GPT-5.2ClosedOpenAI1,420±231,065—
44▼ 1GPT-5 (Medium)ClosedOpenAI1,417±163,036—
45▼ 1GPT-5.3-Codex (Codex Harness)ClosedOpenAI · 1 more variant1,406±142,630—
46▼ 1GPT-5.4 mini (High)ClosedOpenAI1,398±711,823—
47▼ 1GPT-5.1 (Medium)ClosedOpenAI · 1 more variant1,397±124,859—
48▼ 1Claude Sonnet 4.5 (High, 32K, 20250929)ClosedAnthropic · 1 more variant1,393±813,102—
49▼ 1Claude Opus 4.1 (20250805)ClosedAnthropic1,389±116,816—
50▼ 1Grok 4.20 Beta (Reasoning, 0309)ClosedxAI1,376±615,278—

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.