Skip to content
IFAI

Model rankings

1239 models · 5 boards · 2 sources

WebDev arena · People compare web pages built by two models · Published May 25, 2026

Best web builder
claude-opus-4-7-thinkingAnthropic1,567Score
Best open model
glm-5.1Z.ai1,533Score
Best from China
qwen3.7-max-20260517Alibaba1,541Score
Most voted
claude-haiku-4-5-20251001Anthropic20,550Votes
Top three by Score
1claude-opus-4-7-thinkingAnthropic1,567
2claude-opus-4-6-thinkingAnthropic1,542
3qwen3.7-max-20260517Alibaba1,541
Top three open models
1glm-5.1Z.ai · #4 overall1,533
2kimi-k2.6Moonshot AI · #6 overall1,518
3mimo-v2.5-proXiaomi · #13 overall1,471
This week's changes
qwen3.7-max-20260517Coding · #3New
xAI Text to SpeechSpeech · #5New
Fun-Realtime-TTS-PreviewSpeech · #6New
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-opus-4-7-thinkingClosedAnthropic1,567±105,270—
2—claude-opus-4-7ClosedAnthropic1,562±104,862—
3—claude-opus-4-6-thinkingClosedAnthropic1,542±87,919—
4—claude-opus-4-6ClosedAnthropic1,538±78,889—
5—claude-sonnet-4-6ClosedAnthropic1,523±711,120—
6—muse-sparkClosedMeta1,508±161,627—
7—gemini-3.5-flashClosedGoogle1,506±132,213—
8—gpt-5.5-xhigh (codex-harness)ClosedOpenAI1,505±104,126—
9—claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,490±713,063—
10—gpt-5.5-high (codex-harness)ClosedOpenAI1,479±104,348—
11—claude-opus-4-5-20251101ClosedAnthropic1,467±615,300—
12—gpt-5.4-high (codex-harness)ClosedOpenAI1,457±171,483—
13—gemini-3.1-pro-previewClosedGoogle1,448±710,289—
14—gpt-5.5 (codex-harness)ClosedOpenAI1,444±104,145—
15—gemini-3-proClosedGoogle1,438±717,155—
16—gpt-5.4-medium (codex-harness)ClosedOpenAI1,437±161,449—
17—gemini-3-flashClosedGoogle1,437±713,274—
18—gpt-5.3-codex (codex-harness)ClosedOpenAI1,407±122,963—
19—gpt-5.2ClosedOpenAI1,404±171,458—
20—gpt-5.4-mini-highClosedOpenAI1,402±95,497—
21—grok-4.20-beta-0309-reasoningClosedxAI1,395±87,216—
22—gpt-5-mediumClosedOpenAI1,394±133,754—
23—gpt-5.1-mediumClosedOpenAI1,391±96,115—
24▲ 2gpt-5.4ClosedOpenAI1,388±39239—
25—claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,388±715,739—
26▼ 2gemini-3-flash (thinking-minimal)ClosedGoogle1,387±616,396—
27—claude-sonnet-4-5-20250929ClosedAnthropic1,386±618,386—
28—claude-opus-4-1-20250805ClosedAnthropic1,386±98,565—
29▲ 1gemma-4-31bOpenGoogle1,380±113,380$0.000
30▼ 1grok-4.3ClosedxAI1,377±113,482—
31—gpt-5.3-codex (codex-harness)ClosedOpenAI1,373±113,546—
32—gemma-4-26b-a4bOpenGoogle1,360±161,502—
33—gpt-5.1ClosedOpenAI1,340±712,866—
34—gpt-5.2-codexClosedOpenAI1,335±87,766—
35—gpt-5.1-codexClosedOpenAI1,329±106,216—
36—claude-haiku-4-5-20251001ClosedAnthropic1,322±620,550$2.0
37—gemini-3.1-flash-lite-previewClosedGoogle1,248±89,327$0.56
38—gpt-5.1-codex-miniClosedOpenAI1,240±171,443—
39—grok-4-1-fast-reasoningClosedxAI1,234±96,911—
40—grok-4.1-thinkingClosedxAI1,209±201,209—
41—gemini-2.5-proClosedGoogle1,204±133,297—
42—granite-4.1-8bOpenIBM1,202±181,725—
43—mercury-2ClosedInception1,165±23946—
44—grok-4-fast-reasoningClosedxAI1,150±23933—
45—grok-code-fast-1ClosedxAI1,140±22982—

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 “—”.