Skip to content
IFAI

Model rankings

1074 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published March 20, 2026

Most preferred
claude-opus-4-6-thinkingAnthropic1,502Score
Best open model
glm-5Z.ai1,455Score
Best from China
qwen3.5-max-previewAlibaba1,464Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1claude-opus-4-6-thinkingAnthropic1,502
3grok-4.20-beta1xAI1,492
Top three open models
1glm-5Z.ai · #20 overall1,455
2kimi-k2.5-thinkingMoonshot AI · #21 overall1,453
3qwen3.5-397b-a17bAlibaba · #25 overall1,452
This week's changes
Kling 3.0 1080p (Pro)Video · #1New
SkyReels V4Video · #2New
minimax-m2.7Coding · #8New
Grok 4.20 Beta 0309 (Reasoning)Intelligence · #10New
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,502±611,801—
2▲ 1gemini-3.1-pro-previewClosedGoogle1,493±614,677—
3▼ 1grok-4.20-beta1ClosedxAI1,492±77,396—
4—gemini-3-proClosedGoogle1,486±441,762—
5▲ 6gpt-5.4-highClosedOpenAI1,485±94,965—
6▼ 1gpt-5.2-chat-latest-20260210ClosedOpenAI1,482±610,140—
7Newgrok-4.20-beta-0309-reasoningClosedxAI1,481±94,504—
8Newgrok-4.20-multi-agent-beta-0309ClosedxAI1,477±85,010—
9▼ 3gemini-3-flashClosedGoogle · 1 more variant1,475±431,060—
10▼ 2claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,474±437,036—
11▼ 4grok-4.1-thinkingClosedxAI · 1 more variant1,472±443,930—
12▼ 2claude-opus-4-5-20251101ClosedAnthropic1,469±441,976—
13▲ 1claude-sonnet-4-6ClosedAnthropic1,465±69,843—
14Newqwen3.5-max-previewClosedAlibaba1,464±94,252—
15▼ 6gpt-5.3-chat-latestClosedOpenAI1,464±78,942—
16▼ 3gpt-5.4ClosedOpenAI1,463±84,972—
17▼ 5dola-seed-2.0-previewClosedByteDance1,462±610,651—
18Newgpt-5.4-mini-highClosedOpenAI1,456±141,638—
19▼ 4gpt-5.1-highClosedOpenAI1,455±440,759—
20▼ 4glm-5OpenZ.ai1,455±611,093—
21▼ 4kimi-k2.5-thinkingOpenMoonshot AI1,453±516,262—
22▼ 3claude-sonnet-4-5-20250929ClosedAnthropic1,453±353,556—
23▼ 3claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,453±355,811—
24▼ 6ernie-5.0-0110ClosedBaidu1,452±518,715—
25▼ 4qwen3.5-397b-a17bOpenAlibaba1,452±610,431—
26▼ 4ernie-5.0-preview-1203ClosedBaidu · 1 more variant1,450±79,857—
27▼ 3claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,449±350,375—
28▼ 5gemini-2.5-proClosedGoogle1,448±3103,317—
29▼ 4claude-opus-4-1-20250805ClosedAnthropic1,447±378,224—
30Newmimo-v2-proClosedXiaomi1,445±103,531—
31▼ 5gpt-4.5-preview-2025-02-27ClosedOpenAI1,444±614,547—
32▼ 4chatgpt-4o-latest-20250326ClosedOpenAI1,443±383,559—
33▼ 4glm-4.7OpenZ.ai1,443±612,242—
34▼ 7gpt-5.2-highClosedOpenAI1,442±525,328—
35▼ 2gemini-3.1-flash-lite-previewClosedGoogle1,441±95,024$0.56
36▼ 6gpt-5.2ClosedOpenAI1,440±522,231—
37▼ 6gpt-5.1ClosedOpenAI1,439±443,475—
38▼ 4qwen3-max-previewClosedAlibaba1,435±428,066—
39▼ 4gpt-5-highClosedOpenAI1,434±532,470—
40▼ 8kimi-k2.5-instantOpenMoonshot AI1,433±78,257—
41▼ 5o3-2025-04-16ClosedOpenAI1,432±460,698—
42▼ 5grok-4-1-fast-reasoningClosedxAI1,431±437,473—
43▼ 5kimi-k2-thinking-turboOpenMoonshot AI1,430±441,738—
44▼ 5amazon-nova-experimental-chat-26-02-10ClosedAmazon1,429±103,467—
45▼ 5gpt-5-chatClosedOpenAI1,426±432,009—
46▼ 5glm-4.6OpenZ.ai1,426±436,102—
47▼ 4deepseek-v3.2-exp-thinkingOpenDeepSeek · 1 more variant1,425±79,188—
48▼ 3deepseek-v3.2OpenDeepSeek · 1 more variant1,425±436,511—
49▼ 7qwen3-max-2025-09-23ClosedAlibaba1,424±69,273—
50▼ 6claude-opus-4-20250514-thinking-16kClosedAnthropic1,424±437,503—

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 “—”.