Skip to content
IFAI

Model rankings

420 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Text arena · Anonymous head-to-head votes · Published July 1, 2025

Most preferred
gemini-2.5-proGoogle1,463Score
Best open model
deepseek-r1-0528DeepSeek1,413Score
Best from China
deepseek-r1-0528DeepSeek1,413Score
Most voted
claude-3-opus-20240229Anthropic202,641Votes
Top three by Score
1gemini-2.5-proGoogle1,463
2o3-2025-04-16OpenAI1,449
Top three open models
1deepseek-r1-0528DeepSeek · #7 overall1,413
2qwen3-235b-a22b-no-thinkingAlibaba · #12 overall1,396
3deepseek-v3-0324DeepSeek · #13 overall1,396
This week's changes
Solar Pro 2 (Preview) (Reasoning)Intelligence · #38New
Gemma 3n E4B InstructIntelligence · #110New
Gemma 2 27BIntelligence · #102Up 20
Gemma 3 4B InstructIntelligence · #124Up 2
RankChangeModelScore95% intervalVotesPrice $/M
1—deepseek-r1-0528OpenDeepSeek · 1 more variant1,413±512,396—
2▲ 1qwen3-235b-a22b-no-thinkingOpenAlibaba1,396±514,090—
3▼ 1deepseek-v3-0324OpenDeepSeek · 1 more variant1,396±420,171—
4—minimax-m1OpenMiniMax1,391±86,117—
5—hunyuan-turbos-20250416ClosedTencent · 1 more variant1,382±68,244—
6—qwen3-235b-a22bOpenAlibaba1,371±513,817—
7—qwen2.5-maxClosedAlibaba1,368±331,778—
8—qwen-plus-0125ClosedAlibaba1,343±76,055—
9—hunyuan-turbo-0110ClosedTencent1,339±102,510—
10—qwq-32bOpenAlibaba · 1 more variant1,337±418,063—
11—glm-4-plus-0111ClosedZhipu · 1 more variant1,337±66,028—
12—step-2-16k-exp-202412ClosedStepFun1,331±65,126—
13—yi-lightningClosed01 AI1,327±428,968—
14—hunyuan-large-2025-02-10ClosedTencent1,322±73,856—
15—deepseek-v2.5-1210OpenDeepSeek · 1 more variant1,320±67,243—
16—qwen-max-0919OpenAlibaba1,311±417,432—
17—qwen2.5-plus-1127ClosedAlibaba1,311±510,715—
18—hunyuan-standard-2025-02-10ClosedTencent1,310±84,014—
19—qwen2.5-72b-instructOpenAlibaba1,302±341,519—
20▲ 4hunyuan-large-visionClosedTencent1,273±113,905—
21▼ 1qwen2.5-coder-32b-instructOpenAlibaba1,270±85,730—
22▼ 1glm-4-0520ClosedZhipu AI1,268±510,221—
23▼ 1deepseek-coder-v2OpenDeepSeek1,262±415,753—
24▼ 1qwen2-72b-instructOpenAlibaba1,261±338,872—
25—qwen1.5-110b-chatOpenAlibaba1,235±327,430—
26—hunyuan-standard-256kClosedTencent1,233±102,901—
27—qwen1.5-72b-chatOpenAlibaba1,228±340,658—
28—yi-1.5-34b-chatOpen01 AI1,213±425,135—
29—qwen1.5-32b-chatOpenAlibaba1,207±322,765—
30—qwen1.5-14b-chatOpenAlibaba1,187±418,687—
31—yi-34b-chatOpen01 AI1,181±515,917—
32—deepseek-llm-67b-chatOpenDeepSeek1,171±84,988—
33—qwen1.5-7b-chatOpenAlibaba1,145±84,872—
34—qwen-14b-chatOpenAlibaba1,136±95,065—
35—qwen1.5-4b-chatOpenAlibaba1,094±67,816—

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 “—”.