Skip to content
IFAI

Model rankings

740 models · 4 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published November 9, 2025

Most preferred
gemini-2.5-proGoogle1,452Score
Best open model
glm-4.6Z.ai1,429Score
Best from China
qwen3-max-previewAlibaba1,432Score
Most voted
claude-3-opus-20240229Anthropic196,368Votes
Top three by Score
1gemini-2.5-proGoogle1,452
Top three open models
1glm-4.6Z.ai · #11 overall1,429
2deepseek-v3.2-expDeepSeek · #15 overall1,422
3qwen3-235b-a22b-instruct-2507Alibaba · #17 overall1,420
This week's changes
MiniMax-M2Intelligence · #8New
Chirp 3: HDSpeech · #20New
Maya1Speech · #21New
Qwen3 VL 235B A22B (Reasoning)Intelligence · #23New
Sonic 3Speech · #23New
RankChangeModelScore95% intervalVotesPrice $/M
1—gemini-2.5-proClosedGoogle1,452±461,504—
2▲ 1claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,448±612,588—
3▼ 1claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,448±528,241—
4—gpt-4.5-preview-2025-02-27ClosedOpenAI1,442±614,644—
5▲ 2claude-sonnet-4-5-20250929ClosedAnthropic1,441±87,041—
6▲ 3claude-opus-4-1-20250805ClosedAnthropic1,439±440,674—
7▼ 2chatgpt-4o-latest-20250326ClosedOpenAI1,438±447,199—
8—gpt-5-highClosedOpenAI1,436±529,776—
9▼ 3o3-2025-04-16ClosedOpenAI1,434±458,206—
10—qwen3-max-previewClosedAlibaba1,432±524,709—
11—gpt-5-chatClosedOpenAI1,425±528,560—
12—qwen3-max-2025-09-23ClosedAlibaba1,423±69,298—
13▲ 1claude-opus-4-20250514-thinking-16kClosedAnthropic1,423±437,998—
14▼ 1grok-4-fast-chatClosedxAI1,420±87,096—
15▲ 2gpt-4.1-2025-04-14ClosedOpenAI1,412±448,970—
16—claude-opus-4-20250514ClosedAnthropic1,412±445,793—
17▲ 3mistral-medium-2508ClosedMistral · 2 more variants1,411±530,505—
18—grok-3-preview-02-24ClosedxAI1,410±434,176—
19▼ 4grok-4-0709ClosedxAI1,409±435,756—
20▼ 1gemini-2.5-flashClosedGoogle1,408±460,857—
21—gemini-2.5-flash-preview-09-2025ClosedGoogle1,406±613,686—
22—grok-4-fast-reasoningClosedxAI1,403±611,770—
23▲ 2claude-haiku-4-5-20251001ClosedAnthropic1,403±610,144$2.0
24▼ 1o1-2024-12-17ClosedOpenAI1,400±428,039—
25▼ 1claude-sonnet-4-20250514-thinking-32kClosedAnthropic1,399±436,329—
26—gpt-5-mini-highClosedOpenAI1,392±524,340—
27—o4-mini-2025-04-16ClosedOpenAI1,391±446,984—
28▲ 2mai-1-previewClosedMicrosoft AI1,390±518,276—
29▼ 1hunyuan-vision-1.5-thinkingClosedTencent1,390±122,224—
30▼ 1claude-sonnet-4-20250514ClosedAnthropic1,389±441,759—
31—o1-previewClosedOpenAI1,386±531,505—
32—claude-3-7-sonnet-20250219-thinking-32kClosedAnthropic1,386±439,973—
33—hunyuan-t1-20250711ClosedTencent1,385±94,837—
34▲ 1gpt-4.1-mini-2025-04-14ClosedOpenAI1,380±440,575—
35▲ 2gemini-2.5-flash-lite-preview-09-2025-no-thinkingClosedGoogle1,380±613,692—
36▼ 2hunyuan-turbos-20250416ClosedTencent · 1 more variant1,380±611,144—
37▼ 1gemini-2.5-flash-lite-preview-06-17-thinkingClosedGoogle1,375±534,095—
38—qwen2.5-maxClosedAlibaba1,372±433,561—
39—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,371±389,890—
40—claude-3-7-sonnet-20250219ClosedAnthropic1,370±444,614—
41—grok-3-mini-highClosedxAI1,362±517,623—
42—o3-mini-highClosedOpenAI1,362±518,735—
43—gemini-2.0-flash-001ClosedGoogle1,360±445,143—
44—grok-3-mini-betaClosedxAI1,357±523,852—
45—gemini-2.0-flash-lite-preview-02-05ClosedGoogle1,352±425,215—
46—gemini-1.5-pro-002ClosedGoogle1,351±356,012—
47—o3-miniClosedOpenAI1,347±358,891—
48—amazon-nova-experimental-chat-10-09ClosedAmazon1,344±86,275—
49—gpt-4o-2024-05-13ClosedOpenAI1,344±3113,568—
50—qwen-plus-0125ClosedAlibaba1,344±85,861—

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 “—”.