Skip to content
IFAI

Model rankings

1160 models · 5 boards · 2 sources

WebDev arena · People compare web pages built by two models · Published April 23, 2026

Best web builder
claude-opus-4-7-thinkingAnthropic1,572Score
Best open model
glm-5.1Z.ai1,534Score
Best from China
glm-5.1Z.ai1,534Score
Most voted
claude-sonnet-4-5-20250929Anthropic18,382Votes
Top three by Score
1claude-opus-4-7-thinkingAnthropic1,572
2claude-opus-4-6-thinkingAnthropic1,552
3glm-5.1Z.ai1,534
Top three open models
1glm-5.1Z.ai · #3 overall1,534
2kimi-k2.6Moonshot AI · #4 overall1,529
3deepseek-v4-pro-thinkingDeepSeek · #12 overall1,456
This week's changes
GPT-5.5 (xhigh)Intelligence · #1New
GPT Image 2 (high)Image · #1New
Realtime TTS 1.5 MaxSpeech · #1New
kimi-k2.6Coding · #4New
RankChangeModelScore95% intervalVotesPrice $/M
1—glm-5.1OpenZ.ai1,534±132,478—
2Newkimi-k2.6OpenMoonshot AI1,529±171,408—
3Newdeepseek-v4-pro-thinkingOpenDeepSeek1,456±191,066—
4▼ 2glm-4.7OpenZ.ai1,440±104,880—
5▼ 2glm-5OpenZ.ai1,435±95,640—
6▼ 2kimi-k2.5-thinkingOpenMoonshot AI1,430±87,913—
7▼ 2minimax-m2.7OpenMiniMax1,416±103,785—
8▼ 2kimi-k2.5-instantOpenMoonshot AI1,408±113,611—
9▼ 2minimax-m2.1-previewOpenMiniMax1,392±89,274—
10▼ 2qwen3.5-397b-a17bOpenAlibaba1,388±86,715—
11▼ 2minimax-m2.5OpenMiniMax1,384±87,834—
12▼ 2deepseek-v3.2-thinkingOpenDeepSeek · 1 more variant1,368±87,904—
13▼ 2qwen3.5-122b-a10bOpenAlibaba1,363±95,506—
14▼ 2glm-4.6OpenZ.ai1,355±98,349—
15▼ 2qwen3.5-27bOpenAlibaba1,345±95,083—
16▼ 2mimo-v2-flash (non-thinking)OpenXiaomi · 1 more variant1,337±86,736—
17▼ 2kimi-k2-thinking-turboOpenMoonshot AI1,329±615,346—
18▼ 2minimax-m2OpenMiniMax1,304±98,401—
19▼ 2deepseek-v3.2-expOpenDeepSeek1,286±114,870—
20▼ 2qwen3-coder-480b-a35b-instructOpenAlibaba1,281±715,208—
21▼ 2qwen3.5-35b-a3bOpenAlibaba1,248±161,814—
22▼ 2mistral-large-3OpenMistral1,223±201,031—
23▼ 2devstral-2OpenMistral1,199±171,582—

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 “—”.