Skip to content
IFAI

Model rankings

1319 models · 5 boards · 2 sources

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

Best web builder
claude-fable-5Anthropic1,653Score
Best open model
glm-5.2 (max)Z.ai1,584Score
Best from China
glm-5.2 (max)Z.ai1,584Score
Most voted
claude-haiku-4-5-20251001Anthropic23,650Votes
Top three by Score
1claude-fable-5Anthropic1,653
2glm-5.2 (max)Z.ai1,584
3claude-opus-4-8-thinkingAnthropic1,561
Top three open models
1glm-5.2 (max)Z.ai · #2 overall1,584
2glm-5.1Z.ai · #9 overall1,523
3kimi-k2.6Moonshot AI · #11 overall1,514
This week's changes
Reve 2.0Image · #2New
claude-sonnet-5-thinkingCoding · #5New
Fish Audio S2.1 ProSpeech · #15New
OpenAudio S1 MiniSpeech · #50New
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-fable-5ClosedAnthropic1,653±152,100—
2—claude-opus-4-8-thinkingClosedAnthropic · 1 more variant1,561±104,071—
3—claude-opus-4-7-thinkingClosedAnthropic · 1 more variant1,559±88,857—
4Newclaude-sonnet-5-thinkingClosedAnthropic1,551±181,250—
5▼ 1claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,542±711,365—
6▼ 1claude-sonnet-4-6ClosedAnthropic1,522±614,669—
7▼ 1gemini-3.5-flashClosedGoogle1,510±95,817—
8▼ 1gpt-5.5-xhigh (codex-harness)ClosedOpenAI1,501±87,587—
9▼ 1claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,490±713,060—
10▼ 1gpt-5.5-high (codex-harness)ClosedOpenAI1,483±87,770—
11▼ 1claude-opus-4-5-20251101ClosedAnthropic1,466±615,315—
12▼ 1gpt-5.4-high (codex-harness)ClosedOpenAI1,457±171,482—
13▼ 1gpt-5.5 (codex-harness)ClosedOpenAI1,448±87,600—
14▼ 1gemini-3.1-pro-previewClosedGoogle1,445±614,184—
15▼ 1gemini-3-proClosedGoogle1,439±717,152—
16▼ 1gpt-5.4-medium (codex-harness)ClosedOpenAI1,437±161,449—
17▼ 1gemini-3-flashClosedGoogle · 1 more variant1,437±713,270—
18—gpt-5.3-codex (codex-harness)ClosedOpenAI · 1 more variant1,406±122,963—
19—gpt-5.2ClosedOpenAI1,405±171,457—
20—gpt-5.4-mini-highClosedOpenAI1,397±78,682—
21—gpt-5-mediumClosedOpenAI1,395±133,756—
22▼ 5gpt-5.4ClosedOpenAI1,394±22721—
23▼ 1gpt-5.1-mediumClosedOpenAI1,391±96,117—
24▼ 1claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,388±715,749—
25—claude-sonnet-4-5-20250929ClosedAnthropic1,386±618,414—
26▼ 2claude-opus-4-1-20250805ClosedAnthropic1,386±98,568—
27▼ 1grok-4.20-beta-0309-reasoningClosedxAI1,383±710,562—
28▼ 1gemma-4-31bOpenGoogle1,371±95,472$0.000
29▼ 1grok-4.3ClosedxAI1,363±86,838—
30▼ 1gemma-4-26b-a4bOpenGoogle1,359±161,508—
31▼ 1gpt-5.1ClosedOpenAI1,339±712,866—
32▼ 1gpt-5.2-codexClosedOpenAI1,334±87,771—
33▼ 1gpt-5.1-codexClosedOpenAI1,330±106,215—
34▼ 1claude-haiku-4-5-20251001ClosedAnthropic1,327±523,650$2.0
35▼ 1gemini-3.1-flash-lite-previewClosedGoogle1,253±712,826$0.56
36▼ 1gpt-5.1-codex-miniClosedOpenAI1,240±171,445—
37▼ 1grok-4-1-fast-reasoningClosedxAI1,234±96,908—
38▼ 1grok-4.1-thinkingClosedxAI1,209±201,209—
39▼ 1gemini-2.5-proClosedGoogle1,204±133,301—
40▼ 1granite-4.1-8bOpenIBM1,200±181,727—
41▼ 1mercury-2ClosedInception1,165±23948—
42▼ 1grok-4-fast-reasoningClosedxAI1,150±23933—
43▼ 1grok-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 “—”.