Skip to content
IFAI

Model rankings

1239 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published May 27, 2026

Most preferred
claude-opus-4-6-thinkingAnthropic1,502Score
Best open model
glm-5.1Z.ai1,474Score
Best from China
qwen3.7-max-previewAlibaba1,475Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1claude-opus-4-6-thinkingAnthropic1,502
2claude-opus-4-7-thinkingAnthropic1,500
3muse-sparkMeta1,489
Top three open models
1glm-5.1Z.ai · #14 overall1,474
2mimo-v2.5-proXiaomi · #25 overall1,465
3kimi-k2.6Moonshot AI · #26 overall1,462
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-4-6-thinkingClosedAnthropic · 1 more variant1,502±434,186—
2—claude-opus-4-7-thinkingClosedAnthropic · 1 more variant1,500±519,973—
3—muse-sparkClosedMeta1,489±612,228—
4—gemini-3.1-pro-previewClosedGoogle1,487±443,742—
5—gemini-3-proClosedGoogle1,486±441,332—
6—gpt-5.5-highClosedOpenAI1,482±616,573—
7▲ 1gpt-5.4-highClosedOpenAI1,480±528,246—
8▼ 1gemini-3.5-flashClosedGoogle1,479±79,045—
9—gpt-5.5ClosedOpenAI1,476±616,852—
10▲ 1gpt-5.2-chat-latest-20260210ClosedOpenAI1,476±432,280—
11▼ 1grok-4.20-beta1ClosedxAI1,476±524,468—
12▲ 1grok-4.20-beta-0309-reasoningClosedxAI1,475±529,068—
13▼ 1qwen3.7-max-previewClosedAlibaba1,475±103,755—
14▲ 4gpt-5.5-instantClosedOpenAI1,474±524,925—
15—gemini-3-flashClosedGoogle · 1 more variant1,473±430,732—
16▲ 1claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,473±437,130—
17▼ 3grok-4.20-multi-agent-beta-0309ClosedxAI1,472±528,630—
18▼ 2ernie-5.1ClosedBaidu1,470±614,675—
19—claude-sonnet-4-6ClosedAnthropic1,470±527,474—
20▲ 1gpt-5.4ClosedOpenAI1,469±529,672—
21▼ 1claude-opus-4-5-20251101ClosedAnthropic1,469±366,107—
22—grok-4.1-thinkingClosedxAI · 1 more variant1,466±363,569—
23—qwen3.5-max-previewClosedAlibaba1,466±520,212—
24—qwen3.6-max-previewClosedAlibaba1,459±94,648—
25—dola-seed-2.0-proClosedByteDance1,456±437,742—
26▲ 2claude-sonnet-4-5-20250929ClosedAnthropic1,455±376,121—
27—claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,455±377,813—
28▼ 2gpt-5.1-highClosedOpenAI1,455±440,856—
29—gpt-5.4-mini-highClosedOpenAI1,451±526,397—
30▲ 2ernie-5.0-preview-1203ClosedBaidu · 1 more variant1,449±79,752—
31▲ 3claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,449±349,833—
32▲ 1gpt-5.3-chat-latestClosedOpenAI1,449±430,882—
33▲ 2mimo-v2-proClosedXiaomi1,448±522,638—
34▼ 3ernie-5.0-0110ClosedBaidu1,448±434,159—
35▲ 1claude-opus-4-1-20250805ClosedAnthropic1,447±377,373—
36▼ 6grok-4.3ClosedxAI1,447±615,773—
37—gemini-2.5-proClosedGoogle1,446±3122,636—
38—gpt-4.5-preview-2025-02-27ClosedOpenAI1,445±614,547—
39—qwen3.6-plusClosedAlibaba1,444±518,202—
40—chatgpt-4o-latest-20250326ClosedOpenAI1,443±382,471—
41▲ 1gpt-5.1ClosedOpenAI1,439±443,501—
42▼ 1gpt-5.2-highClosedOpenAI1,438±446,111—
43▲ 2longcat-flash-chat-2602-expClosedMeituan1,436±523,731—
44▲ 2qwen3-max-previewClosedAlibaba1,435±427,736—
45▼ 1gpt-5.2ClosedOpenAI1,435±446,492—
46▲ 1gpt-5-highClosedOpenAI1,434±531,947—
47▼ 4gemini-3.1-flash-lite-previewClosedGoogle1,433±435,135$0.56
48▲ 1o3-2025-04-16ClosedOpenAI1,431±459,775—
49▼ 1grok-4-1-fast-reasoningClosedxAI1,431±354,616—
50—amazon-nova-experimental-chat-26-02-10ClosedAmazon1,427±103,418—

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 “—”.