Skip to content
IFAI

Model rankings

1275 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published June 10, 2026

Most preferred
claude-fable-5Anthropic1,510Score
Best open model
glm-5.1Z.ai1,475Score
Best from China
glm-5.1Z.ai1,475Score
Most voted
claude-3-opus-20240229Anthropic194,909Votes
Top three by Score
1claude-fable-5Anthropic1,510
2claude-opus-4-6-thinkingAnthropic1,504
3claude-opus-4-7-thinkingAnthropic1,502
Top three open models
1glm-5.1Z.ai · #12 overall1,475
2mimo-v2.5-proXiaomi · #25 overall1,466
3kimi-k2.6Moonshot AI · #28 overall1,462
This week's changes
claude-fable-5Coding · #1New
HiDream-O1-Image-1.5Image · #3New
MAI-Image-2.5 (Foundry)Image · #12New
RankChangeModelScore95% intervalVotesPrice $/M
1Newclaude-fable-5ClosedAnthropic1,510±112,883—
2▼ 1claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,504±442,797—
3▼ 1claude-opus-4-7-thinkingClosedAnthropic · 1 more variant1,502±528,900—
4▼ 1muse-sparkClosedMeta1,487±613,511—
5▼ 1gemini-3.1-pro-previewClosedGoogle1,487±455,403—
6▼ 1gemini-3-proClosedGoogle1,486±441,317—
7▼ 1claude-opus-4-8-thinkingClosedAnthropic · 1 more variant1,486±79,190—
8▼ 1gpt-5.5-highClosedOpenAI1,481±524,620—
9▼ 1gpt-5.4-highClosedOpenAI1,479±437,120—
10▼ 1gemini-3.5-flashClosedGoogle1,477±710,113—
11▼ 1gpt-5.2-chat-latest-20260210ClosedOpenAI1,475±434,387—
12▲ 1qwen3.7-max-previewClosedAlibaba1,474±103,744—
13▼ 2grok-4.20-beta1ClosedxAI1,474±526,782—
14▼ 2gpt-5.5ClosedOpenAI1,474±525,255—
15—grok-4.20-beta-0309-reasoningClosedxAI1,474±438,420—
16▼ 2gemini-3-flashClosedGoogle · 1 more variant1,473±430,718—
17—grok-4.20-multi-agent-beta-0309ClosedxAI1,473±437,581—
18▼ 2claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,473±437,098—
19▼ 1gpt-5.5-instantClosedOpenAI1,472±526,225—
20▼ 1claude-sonnet-4-6ClosedAnthropic1,471±435,722—
21—claude-opus-4-5-20251101ClosedAnthropic1,469±371,063—
22▼ 2ernie-5.1ClosedBaidu1,469±521,878—
23—gpt-5.4ClosedOpenAI1,468±439,393—
24▼ 2grok-4.1-thinkingClosedxAI · 1 more variant1,466±365,495—
25▼ 1qwen3.5-max-previewClosedAlibaba1,465±521,470—
26▼ 1qwen3.6-max-previewClosedAlibaba1,460±85,188—
27—claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,456±382,387—
28▼ 2dola-seed-2.0-proClosedByteDance1,455±446,537—
29▼ 1claude-sonnet-4-5-20250929ClosedAnthropic1,455±380,893—
30▼ 1gpt-5.1-highClosedOpenAI1,455±440,830—
31▼ 1minimax-m3ClosedMiniMax1,451±77,782$0.52
32▼ 1ernie-5.0-preview-1203ClosedBaidu · 1 more variant1,449±79,751—
33▲ 1claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,449±349,804—
34▼ 1mimo-v2-proClosedXiaomi1,449±524,482—
35▼ 3gpt-5.4-mini-highClosedOpenAI1,449±435,690—
36▼ 1gpt-5.3-chat-latestClosedOpenAI1,449±432,965—
37—claude-opus-4-1-20250805ClosedAnthropic1,447±377,352—
38▼ 2ernie-5.0-0110ClosedBaidu1,447±435,227—
39—gemini-2.5-proClosedGoogle1,446±3124,473—
40—gpt-4.5-preview-2025-02-27ClosedOpenAI1,445±614,547—
41—qwen3.6-plusClosedAlibaba1,444±525,898—
42▼ 4grok-4.3ClosedxAI1,443±524,424—
43▼ 1chatgpt-4o-latest-20250326ClosedOpenAI1,443±382,455—
44▼ 1gpt-5.1ClosedOpenAI1,439±443,470—
45▼ 1gpt-5.2-highClosedOpenAI1,438±447,930—
46▲ 1longcat-flash-chat-2602-expClosedMeituan1,435±528,117—
47▼ 1qwen3-max-previewClosedAlibaba1,435±427,716—
48▼ 3gpt-5.2ClosedOpenAI1,435±455,819—
49▼ 1gpt-5-highClosedOpenAI1,434±531,932—
50▼ 1gemini-3.1-flash-lite-previewClosedGoogle1,433±444,683$0.56

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 “—”.