Skip to content
IFAI

Model rankings

1209 models · 5 boards · 2 sources

‹
Week of May 11, 2026
June 22, 202612 changesJune 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changesMay 25, 202617 changesMay 18, 202616 changesMay 11, 202665 changesMay 4, 202616 changesApril 27, 202624 changesApril 20, 202627 changesApril 13, 202637 changesApril 6, 202641 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published May 14, 2026

Most preferred
claude-opus-4-6-thinkingAnthropic1,502Score
Best open model
glm-5.1Z.ai1,472Score
Best from China
ernie-5.1Baidu1,472Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1claude-opus-4-6-thinkingAnthropic1,502
2claude-opus-4-7-thinkingAnthropic1,500
3muse-sparkMeta1,490
Top three open models
1glm-5.1Z.ai · #16 overall1,472
2mimo-v2.5-proXiaomi · #23 overall1,463
3kimi-k2.6Moonshot AI · #24 overall1,461
This week's changes
gpt-5.5-xhigh (codex-harness)Coding · #7New
HiDream-O1-Image-Dev-2604Image · #11New
HiDream-O1-ImageImage · #31New
JT-35B-FlashIntelligence · #67New
granite-4.1-8bCoding · #68New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreLowest price
RankChangeModelScore95% intervalVotesPrice $/M
1▲ 1claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,502±425,736—
2▼ 1claude-opus-4-7-thinkingClosedAnthropic · 1 more variant1,500±611,197—
3▲ 1muse-sparkClosedMeta1,490±610,785—
4▼ 1gemini-3.1-pro-previewClosedGoogle1,489±431,925—
5—gemini-3-proClosedGoogle1,486±441,331—
6—gpt-5.5-highClosedOpenAI1,484±78,595—
7▲ 2gpt-5.4-highClosedOpenAI1,479±519,345—
8▼ 1grok-4.20-beta1ClosedxAI1,479±521,190—
9▼ 1gpt-5.2-chat-latest-20260210ClosedOpenAI1,477±426,000—
10▲ 1gpt-5.5ClosedOpenAI1,476±78,686—
11▼ 1grok-4.20-beta-0309-reasoningClosedxAI1,476±519,765—
12—grok-4.20-multi-agent-beta-0309ClosedxAI1,475±519,883—
13—gemini-3-flashClosedGoogle · 1 more variant1,473±430,750—
14—claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,473±437,126—
15—gpt-5.5-instantClosedOpenAI1,472±85,874—
16▲ 3claude-sonnet-4-6ClosedAnthropic1,468±519,224—
17▲ 1grok-4.1-thinkingClosedxAI · 1 more variant1,468±357,580—
18▼ 2claude-opus-4-5-20251101ClosedAnthropic1,467±357,071—
19▼ 2gpt-5.4ClosedOpenAI1,467±520,253—
20—gpt-5.4-mini-highClosedOpenAI1,455±517,231—
21▲ 1gpt-5.1-highClosedOpenAI1,455±440,851—
22▼ 1grok-4.3ClosedxAI1,454±77,457—
23—claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,454±369,268—
24—claude-sonnet-4-5-20250929ClosedAnthropic1,453±367,445—
25—gemma-4-31bOpenGoogle1,451±85,829$0.000
26▲ 1gpt-5.3-chat-latestClosedOpenAI1,449±524,856—
27▼ 1claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,449±349,833—
28—gemini-2.5-proClosedGoogle1,447±3117,010—
29—claude-opus-4-1-20250805ClosedAnthropic1,447±377,396—
30—gpt-4.5-preview-2025-02-27ClosedOpenAI1,444±614,547—
31—chatgpt-4o-latest-20250326ClosedOpenAI1,443±382,480—
32—gpt-5.2-highClosedOpenAI1,440±440,309—
33—gpt-5.1ClosedOpenAI1,439±443,500—
34—gemini-3.1-flash-lite-previewClosedGoogle1,438±525,946$0.56
35—gemma-4-26b-a4bOpenGoogle1,438±85,776—
36—gpt-5.2ClosedOpenAI1,436±437,483—
37—gpt-5-highClosedOpenAI1,434±531,960—
38—grok-4-1-fast-reasoningClosedxAI1,431±352,196—
39—o3-2025-04-16ClosedOpenAI1,431±459,771—
40—amazon-nova-experimental-chat-26-02-10ClosedAmazon1,428±103,424—
41—gpt-5-chatClosedOpenAI1,427±431,611—
42—claude-opus-4-20250514-thinking-16kClosedAnthropic1,424±436,922—
43—grok-4-fast-chatClosedxAI1,421±86,820—
44—amazon-nova-experimental-chat-26-01-10ClosedAmazon1,415±103,412—
45—gpt-4.1-2025-04-14ClosedOpenAI1,413±451,016—
46—claude-opus-4-20250514ClosedAnthropic1,412±444,237—
47—grok-3-preview-02-24ClosedxAI1,412±432,909—
48—gemini-2.5-flashClosedGoogle1,411±3116,697—
49—grok-4-0709ClosedxAI1,410±441,417—
50—claude-haiku-4-5-20251001ClosedAnthropic1,410±369,160$2.0

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 “—”.