Skip to content
IFAI

Model rankings

1275 models · 5 boards · 2 sources

WebDev arena · People compare web pages built by two models · Published June 10, 2026

Best web builder
claude-fable-5Anthropic1,665Score
Best open model
glm-5.1Z.ai1,532Score
Best from China
qwen3.7-max-20260517Alibaba1,534Score
Most voted
claude-haiku-4-5-20251001Anthropic21,787Votes
Top three by Score
1claude-fable-5Anthropic1,665
2claude-opus-4-7-thinkingAnthropic1,566
3claude-opus-4-8-thinkingAnthropic1,559
Top three open models
1glm-5.1Z.ai · #6 overall1,532
2kimi-k2.6Moonshot AI · #9 overall1,515
3mimo-v2.5-proXiaomi · #16 overall1,468
This week's changes
claude-fable-5Coding · #1New
HiDream-O1-Image-1.5Image · #3New
MAI-Image-2.5 (Foundry)Image · #12New
RankChangeModelScore95% intervalVotesPrice $/M
1Newclaude-fable-5ClosedAnthropic1,665±201,228—
2▼ 1claude-opus-4-7-thinkingClosedAnthropic · 1 more variant1,566±96,719—
3▼ 1claude-opus-4-8-thinkingClosedAnthropic · 1 more variant1,559±152,033—
4▼ 1claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,542±79,307—
5▼ 1claude-sonnet-4-6ClosedAnthropic1,523±712,579—
6▼ 1muse-sparkClosedMeta1,508±161,627—
7▼ 1gemini-3.5-flashClosedGoogle1,506±132,210—
8▼ 1gpt-5.5-xhigh (codex-harness)ClosedOpenAI1,501±95,522—
9▼ 1claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,490±713,058—
10▼ 1gpt-5.5-high (codex-harness)ClosedOpenAI1,482±95,731—
11▼ 1claude-opus-4-5-20251101ClosedAnthropic1,467±615,297—
12▼ 1gpt-5.4-high (codex-harness)ClosedOpenAI1,457±171,482—
13▼ 1gpt-5.5 (codex-harness)ClosedOpenAI1,449±95,576—
14▼ 1gemini-3.1-pro-previewClosedGoogle1,447±611,745—
15▼ 1gemini-3-proClosedGoogle1,439±717,155—
16▼ 1gpt-5.4-medium (codex-harness)ClosedOpenAI1,437±161,449—
17▼ 1gemini-3-flashClosedGoogle · 1 more variant1,437±713,276—
18▼ 1gpt-5.3-codex (codex-harness)ClosedOpenAI · 1 more variant1,407±122,963—
19▼ 1gpt-5.2ClosedOpenAI1,405±171,457—
20▼ 1gpt-5.4-mini-highClosedOpenAI1,399±86,806—
21▼ 1gpt-5-mediumClosedOpenAI1,394±133,754—
22▲ 1gpt-5.4ClosedOpenAI1,392±33331—
23▼ 1gpt-5.1-mediumClosedOpenAI1,391±96,118—
24▼ 3grok-4.20-beta-0309-reasoningClosedxAI1,390±78,557—
25▼ 1claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,388±715,740—
26▼ 1claude-opus-4-1-20250805ClosedAnthropic1,386±98,566—
27▼ 1claude-sonnet-4-5-20250929ClosedAnthropic1,386±618,389—
28▼ 1gemma-4-31bOpenGoogle1,377±104,160$0.000
29▼ 1grok-4.3ClosedxAI1,369±94,824—
30▼ 1gemma-4-26b-a4bOpenGoogle1,360±161,501—
31▼ 1gpt-5.1ClosedOpenAI1,340±712,866—
32▼ 1gpt-5.2-codexClosedOpenAI1,334±87,764—
33▼ 1gpt-5.1-codexClosedOpenAI1,329±106,218—
34▼ 1claude-haiku-4-5-20251001ClosedAnthropic1,324±521,787$2.0
35▼ 1gemini-3.1-flash-lite-previewClosedGoogle1,248±710,720$0.56
36▼ 1gpt-5.1-codex-miniClosedOpenAI1,240±171,444—
37▼ 1grok-4-1-fast-reasoningClosedxAI1,234±96,910—
38▼ 1grok-4.1-thinkingClosedxAI1,209±201,209—
39▼ 1gemini-2.5-proClosedGoogle1,204±133,299—
40▼ 1granite-4.1-8bOpenIBM1,201±181,728—
41▼ 1mercury-2ClosedInception1,165±23948—
42▼ 1grok-4-fast-reasoningClosedxAI1,150±23934—
43▼ 1grok-code-fast-1ClosedxAI1,140±22981—

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 “—”.