Skip to content
IFAI

Model rankings

906 models · 5 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published December 30, 2025

Most preferred
gemini-3-proGoogle1,490Score
Best open model
glm-4.7Z.ai1,439Score
Best from China
ernie-5.0-preview-1203Baidu1,448Score
Most voted
claude-3-opus-20240229Anthropic196,365Votes
Top three by Score
1gemini-3-proGoogle1,490
2gemini-3-flashGoogle1,480
Top three open models
1glm-4.7Z.ai · #17 overall1,439
2kimi-k2-thinking-turboMoonshot AI · #23 overall1,430
3glm-4.6Z.ai · #25 overall1,425
This week's changes
Speech 2.6 HDSpeech · #2New
Speech 2.6 TurboSpeech · #3New
minimax-m2.1-previewCoding · #5New
Multilingual v2Speech · #7New
GLM-4.7 (Reasoning)Intelligence · #8New
RankChangeModelScore95% intervalVotesPrice $/M
1—gemini-3-proClosedGoogle1,490±521,938—
2—gemini-3-flashClosedGoogle1,480±87,020—
3—grok-4.1-thinkingClosedxAI · 1 more variant1,477±522,618—
4—claude-opus-4-5-20251101-thinking-32kClosedAnthropic1,470±614,992—
5—claude-opus-4-5-20251101ClosedAnthropic1,467±615,914—
6—gpt-5.1-highClosedOpenAI1,458±519,416—
7—gemini-2.5-proClosedGoogle1,451±382,231—
8—claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic1,450±433,533—
9—claude-opus-4-1-20250805-thinking-16kClosedAnthropic1,448±449,310—
10▲ 1ernie-5.0-preview-1203ClosedBaidu1,448±94,697—
11▼ 1claude-sonnet-4-5-20250929ClosedAnthropic1,446±529,093—
12—gpt-5.2ClosedOpenAI1,443±122,466—
13—gpt-4.5-preview-2025-02-27ClosedOpenAI1,443±614,646—
14—claude-opus-4-1-20250805ClosedAnthropic1,442±362,378—
15—chatgpt-4o-latest-20250326ClosedOpenAI1,441±369,532—
16—gpt-5.2-highClosedOpenAI1,439±96,225—
17—gpt-5.1ClosedOpenAI1,438±520,928—
18—gpt-5-highClosedOpenAI1,436±532,735—
19—o3-2025-04-16ClosedOpenAI1,434±461,343—
20—qwen3-max-previewClosedAlibaba1,434±528,017—
21—grok-4-1-fast-reasoningClosedxAI1,431±615,352—
22—gpt-5-chatClosedOpenAI1,425±432,013—
23—qwen3-max-2025-09-23ClosedAlibaba1,424±69,212—
24—claude-opus-4-20250514-thinking-16kClosedAnthropic1,423±437,682—
25—grok-4-fast-chatClosedxAI1,421±87,030—
26—gpt-4.1-2025-04-14ClosedOpenAI1,412±452,332—
27▲ 1mistral-medium-2508ClosedMistral · 2 more variants1,412±450,801—
28▼ 1claude-opus-4-20250514ClosedAnthropic1,412±445,430—
29—grok-3-preview-02-24ClosedxAI1,410±434,035—
30—grok-4-0709ClosedxAI1,409±442,369—
31—gemini-2.5-flashClosedGoogle1,408±381,715—
32—gemini-2.5-flash-preview-09-2025ClosedGoogle1,405±433,367—
33▲ 1grok-4-fast-reasoningClosedxAI1,402±518,789—
34▼ 1claude-haiku-4-5-20251001ClosedAnthropic1,402±432,078$2.0
35—o1-2024-12-17ClosedOpenAI1,401±428,039—
36—claude-sonnet-4-20250514-thinking-32kClosedAnthropic1,399±436,040—
37—gpt-5-mini-highClosedOpenAI1,392±527,312—
38—hunyuan-vision-1.5-thinkingClosedTencent1,391±122,202—
39—o4-mini-2025-04-16ClosedOpenAI1,391±446,671—
40—mai-1-previewClosedMicrosoft AI1,391±518,095—
41—claude-sonnet-4-20250514ClosedAnthropic1,389±441,456—
42—o1-previewClosedOpenAI1,387±531,505—
43—claude-3-7-sonnet-20250219-thinking-32kClosedAnthropic1,387±439,799—
44—hunyuan-t1-20250711ClosedTencent1,385±94,800—
45—gpt-4.1-mini-2025-04-14ClosedOpenAI1,381±440,348—
46—hunyuan-turbos-20250416ClosedTencent · 1 more variant1,381±611,084—
47—gemini-2.5-flash-lite-preview-09-2025-no-thinkingClosedGoogle1,378±434,924—
48—gemini-2.5-flash-lite-preview-06-17-thinkingClosedGoogle1,375±433,787—
49—qwen2.5-maxClosedAlibaba1,373±433,488—
50—claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant1,372±389,711—

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 “—”.