Skip to content
IFAI

Model rankings

1090 models · 5 boards · 2 sources

WebDev arena · People compare web pages built by two models · Published April 2, 2026

Best web builder
claude-opus-4-6-thinkingAnthropic1,545Score
Best open model
glm-5Z.ai1,439Score
Best from China
qwen3.6-plus-previewAlibaba1,449Score
Most voted
claude-sonnet-4-5-20250929Anthropic18,568Votes
Top three by Score
1claude-opus-4-6-thinkingAnthropic1,545
2claude-sonnet-4-6Anthropic1,521
Top three open models
1glm-5Z.ai · #8 overall1,439
2glm-4.7Z.ai · #9 overall1,438
3kimi-k2.5-thinkingMoonshot AI · #13 overall1,428
This week's changes
qwen3.6-plus-previewCoding · #7New
gpt-5.4-mini-highCoding · #28New
Nemotron Cascade 2 30B A3BIntelligence · #78New
GPT-4Intelligence · #204New
Solar MiniIntelligence · #217New
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,545±123,716—
2—claude-sonnet-4-6ClosedAnthropic1,521±97,144—
3—claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,490±713,249—
4—claude-opus-4-5-20251101ClosedAnthropic1,465±714,289—
5—gpt-5.4-high (codex-harness)ClosedOpenAI1,456±171,495—
6—gemini-3.1-pro-previewClosedGoogle1,455±95,511—
7—gemini-3-proClosedGoogle1,437±717,153—
8—gemini-3-flashClosedGoogle · 1 more variant1,435±713,267—
9—gpt-5.4-medium (codex-harness)ClosedOpenAI1,426±161,579—
10—gpt-5.3-codex (codex-harness)ClosedOpenAI1,406±122,974—
11—gpt-5.2ClosedOpenAI1,402±171,460—
12—gpt-5-mediumClosedOpenAI1,392±133,753—
13—gpt-5.1-mediumClosedOpenAI1,389±96,121—
14—claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,387±615,915—
15—claude-sonnet-4-5-20250929ClosedAnthropic1,386±618,568—
16▲ 1grok-4.20-beta-0309-reasoningClosedxAI1,385±123,099—
17▼ 1claude-opus-4-1-20250805ClosedAnthropic1,384±98,568—
18Newgpt-5.4-mini-highClosedOpenAI1,382±181,240—
19▼ 1gpt-5.1ClosedOpenAI1,338±712,868—
20▼ 1gpt-5.2-codexClosedOpenAI1,334±87,955—
21▼ 1gpt-5.1-codexClosedOpenAI1,327±96,222—
22▼ 1claude-haiku-4-5-20251001ClosedAnthropic1,311±616,658$2.0
23—gpt-5.1-codex-miniClosedOpenAI1,237±171,443—
24▼ 2gemini-3.1-flash-lite-previewClosedGoogle1,236±105,352$0.56
25▼ 1grok-4-1-fast-reasoningClosedxAI1,232±96,916—
26▼ 1grok-4.1-thinkingClosedxAI1,206±201,209—
27▼ 1gemini-2.5-proClosedGoogle1,201±133,295—
28▼ 1mercury-2ClosedInception1,181±211,107—
29▼ 1grok-4-fast-reasoningClosedxAI1,147±23933—
30▼ 1grok-code-fast-1ClosedxAI1,138±22983—

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 “—”.