Skip to content
IFAI

Model rankings

1542 models · 5 boards · 2 sources

WebDev arena · People compare web pages built by two models · Published October 18, 2026

Best web builder
Claude Opus 5.5 (Max)Anthropic1,806Score
Best open model
Best from China
Qwen3.8-Max (0902)Alibaba1,674Score
Most voted
Claude Haiku 4.5 (20251001)Anthropic29,060Votes
Top three by Score
1Claude Opus 5.5 (Max)Anthropic1,806
2GPT-6 Astra (Max)OpenAI1,776
Top three open models
1DeepSeek-V4.1-Flash-20261017 (Max)DeepSeek · #10 overall1,670
2Kimi K3 (Max)Moonshot AI · #12 overall1,655
3MiMo-V2.6-FlashXiaomi · #15 overall1,633
This week's changes
Claude Opus 5.5 (Max)Coding · #1New
Eleven v4 TurboSpeech · #1New
GPT-6 Astra (Max)Coding · #2New
GPT-6.1 Sol (Max)Coding · #4New
RankChangeModelScore95% intervalVotesPrice $/M
1NewDeepSeek-V4.1-Flash-20261017 (Max)OpenDeepSeek1,670±171,417—
2NewKimi K3 (Max)OpenMoonshot AI1,655±619,426$6.0
3NewMiMo-V2.6-FlashOpenXiaomi1,633±105,195$0.18
4NewHy4 previewOpenTencent1,631±104,798—
5NewQwen3.8-Flash-NextOpenAlibaba1,629±88,278—
6NewMiMo-V2.6-ProOpenXiaomi1,626±104,959$0.54
7NewGLM-5.3 (Max)OpenZ.ai1,622±89,729$2.2
8NewDeepSeek-V4.1-Flash-20260910 (Max)OpenDeepSeek1,619±113,533—
9NewGLM-5.3-FlashOpenZ.ai1,607±718,002$0.24
10NewGLM-5.2 (Max)OpenZ.ai1,604±616,602—
11NewQwen3.8-27BOpenAlibaba1,592±716,172$1.1
12NewDeepSeek-V4-Flash (High)OpenDeepSeek1,582±94,953—
13NewDeepSeek-V4-Pro (High, 20260813)OpenDeepSeek1,582±94,715—
14NewMuse Spark Open (Max)OpenMeta1,524±171,337$2.0
15NewKimi K2.6OpenMoonshot AI1,510±710,167—
16NewGLM-5.1OpenZ.ai1,508±710,703—
17NewHy3OpenTencent1,507±86,201—
18NewMiniMax-M3OpenMiniMax1,482±619,670$0.52
19NewMiMo-V2.5-ProOpenXiaomi1,481±522,366—
20NewKimi K2.7 CodeOpenMoonshot AI1,474±94,963—
21NewDeepSeek-V4-Pro Preview (High)OpenDeepSeek1,465±613,157—
22NewDeepSeek-V4-ProOpenDeepSeek1,447±613,974—
23NewMiMo-V2.5OpenXiaomi1,439±614,912—
24Newbeam-1.0-501b-a23bOpenReflection1,437±132,907—
25NewKimi K2.5 (Thinking)OpenMoonshot AI1,437±520,093—
26NewGLM-5OpenZ.ai1,436±87,494—
27NewGLM-4.7OpenZ.ai1,435±124,007—
28NewDeepSeek-V4-Flash Preview (High)OpenDeepSeek1,431±710,106—
29NewInklingOpenThinking Machines1,414±615,683$1.8
30NewInkling-SmallOpenThinking Machines1,410±95,328$0.52
31NewKimi K2.5 (Instant)OpenMoonshot AI1,406±123,266—
32NewQwen3.5-397B-A17BOpenAlibaba1,400±521,156—
33NewMiniMax-M2.7OpenMiniMax1,399±615,970—
34NewMiniMax-M2.5OpenMiniMax1,386±87,629—
35NewMiniMax-M2.1 PreviewOpenMiniMax1,384±107,640—
36NewGemma 4 31BOpenGoogle1,368±614,592$0.000
37NewDeepSeek-V3.2 (Thinking)OpenDeepSeek1,363±96,918—
38NewQwen3.5-122B-A10BOpenAlibaba1,361±88,234—
39NewGemma 4 26B A4BOpenGoogle1,360±171,501—
40NewQwen3.5-27BOpenAlibaba1,358±87,781—
41NewHy3 previewOpenTencent1,357±171,445—
42NewMuse GlimmerOpenMeta1,355±161,646$0.52
43NewLaguna M.1OpenPoolside1,350±95,395—
44NewGLM-4.6OpenZ.ai1,341±116,781—
45NewMiMo-V2-Flash (Non-Thinking)OpenXiaomi1,330±105,690—
46NewDeepSeek-V3.2OpenDeepSeek1,326±89,383—
47NewKimi K2 Thinking TurboOpenMoonshot AI1,322±713,095—
48NewLaguna XS.2OpenPoolside1,303±114,227—
49NewMiniMax-M2OpenMiniMax1,297±116,718—
50NewMiMo-V2-Flash (Thinking)OpenXiaomi1,293±161,685—

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 “—”.