Skip to content
IFAI

Model rankings

1007 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published February 11, 2026

Most preferred
claude-opus-4-6-thinkingAnthropic1,506Score
Best open model
glm-5Z.ai1,452Score
Best from China
dola-seed-2.0-previewByteDance1,461Score
Most voted
claude-3-opus-20240229Anthropic194,904Votes
Top three by Score
1claude-opus-4-6-thinkingAnthropic1,506
3gemini-3-proGoogle1,486
Top three open models
1glm-5Z.ai · #10 overall1,452
2kimi-k2.5-thinkingMoonshot AI · #17 overall1,447
3glm-4.7Z.ai · #21 overall1,441
This week's changes
Riverflow 2.0Image · #2New
Vidu Q3 ProVideo · #2New
gemini-3.1-pro-previewCoding · #3New
glm-5Coding · #5New
RankChangeModelScore95% intervalVotesPrice $/M
1—claude-opus-4-6-thinkingClosedAnthropic · 1 more variant1,506±103,922—
2—gemini-3.1-pro-previewClosedGoogle1,500±94,074—
3—gemini-3-proClosedGoogle1,486±435,697—
4—grok-4.1-thinkingClosedxAI · 1 more variant1,475±435,401—
5—gemini-3-flashClosedGoogle · 1 more variant1,473±526,326—
6—claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,471±527,513—
7—claude-opus-4-5-20251101ClosedAnthropic1,467±432,417—
8Newdola-seed-2.0-previewClosedByteDance1,461±32296—
9▼ 1gpt-5.1-highClosedOpenAI1,457±431,719—
10▼ 1ernie-5.0-0110ClosedBaidu1,451±611,263—
11▼ 1claude-sonnet-4-5-20250929ClosedAnthropic1,451±443,701—
12▼ 1claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,450±445,976—
13—ernie-5.0-preview-1203ClosedBaidu · 1 more variant1,449±79,756—
14▼ 2gemini-2.5-proClosedGoogle1,449±394,981—
15▼ 1claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,449±449,857—
16▼ 1claude-opus-4-1-20250805ClosedAnthropic1,445±375,021—
17▼ 1gpt-4.5-preview-2025-02-27ClosedOpenAI1,444±614,549—
18▼ 1chatgpt-4o-latest-20250326ClosedOpenAI1,442±382,484—
19—gpt-5.1ClosedOpenAI1,438±433,940—
20—gpt-5.2ClosedOpenAI1,437±612,999—
21▼ 3gpt-5.2-highClosedOpenAI1,436±616,346—
22▼ 1gpt-5-highClosedOpenAI1,435±532,584—
23▼ 1qwen3-max-previewClosedAlibaba1,434±527,800—
24▼ 1o3-2025-04-16ClosedOpenAI1,433±461,308—
25▼ 1grok-4-1-fast-reasoningClosedxAI1,431±428,395—
26▼ 1gpt-5-chatClosedOpenAI1,426±431,774—
27▼ 1qwen3-max-2025-09-23ClosedAlibaba1,425±69,208—
28▼ 1claude-opus-4-20250514-thinking-16kClosedAnthropic1,424±437,939—
29▼ 1grok-4-fast-chatClosedxAI1,422±86,984—
30—gpt-4.1-2025-04-14ClosedOpenAI1,413±452,163—
31▼ 2claude-opus-4-20250514ClosedAnthropic1,413±445,537—
32—grok-3-preview-02-24ClosedxAI1,411±433,967—
33▼ 2mistral-medium-2508ClosedMistral · 2 more variants1,411±363,158—
34▼ 1gemini-2.5-flashClosedGoogle1,411±394,232—
35▼ 1grok-4-0709ClosedxAI1,410±442,080—
36▼ 1gemini-2.5-flash-preview-09-2025ClosedGoogle1,405±432,822—
37▼ 1claude-haiku-4-5-20251001ClosedAnthropic1,404±444,699$2.0
38▼ 1grok-4-fast-reasoningClosedxAI1,404±518,594—
39▼ 1o1-2024-12-17ClosedOpenAI1,402±427,822—
40▼ 1claude-sonnet-4-20250514-thinking-32kClosedAnthropic1,400±436,181—
41▼ 1amazon-nova-experimental-chat-12-10ClosedAmazon1,395±103,710—
42▼ 1hunyuan-vision-1.5-thinkingClosedTencent1,393±122,223—
43▼ 1mai-1-previewClosedMicrosoft AI1,392±518,103—
44▼ 1o4-mini-2025-04-16ClosedOpenAI1,391±446,636—
45▼ 1gpt-5-mini-highClosedOpenAI1,391±527,106—
46▼ 1claude-sonnet-4-20250514ClosedAnthropic1,390±441,619—
47▼ 1claude-3-7-sonnet-20250219-thinking-32kClosedAnthropic1,389±439,877—
48▼ 1o1-previewClosedOpenAI1,388±531,120—
49▼ 1hunyuan-t1-20250711ClosedTencent1,387±94,796—
50▼ 1hunyuan-turbos-20250416ClosedTencent · 1 more variant1,382±611,052—

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 “—”.