Skip to content
IFAI

Model rankings

298 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated April 8, 2025

Smartest
Best open model
DeepSeek R1DeepSeek60.2Intelligence
Best from China
DeepSeek R1DeepSeek60.2Intelligence
Top three by Intelligence
2o3-mini (high)OpenAI65.5
3o1OpenAI61.9
Top three open models
1DeepSeek R1DeepSeek · #4 overall60.2
2QwQ 32BAlibaba · #5 overall58.1
3DeepSeek V3 0324 (Mar' 25)DeepSeek · #8 overall53.2
This week's changes
Llama 4 MaverickIntelligence · #11New
Llama 4 ScoutIntelligence · #22New
Gemma 3 12B InstructIntelligence · #51New
Gemma 3 4B InstructIntelligence · #71New
Gemini 1.5 Flash (Sep '24)Intelligence · #35Up 20
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewLlama 4 MaverickOpenMeta50.3———
2NewLlama 4 ScoutOpenMeta43.0———
3▼ 2Llama 3.3 Instruct 70BOpenMeta41.1———
4▼ 2Llama 3.1 Instruct 405BOpenMeta40.5———
5▼ 2Phi-4OpenMicrosoft Azure40.2———
6▼ 2Llama 3.3 Nemotron Super 49B v1OpenNVIDIA39.3———
7▼ 2Gemma 3 27B InstructOpenGoogle37.6———
8▼ 2Llama 3.1 Nemotron Instruct 70BOpenNVIDIA37.3———
9▼ 2Llama 3.1 Instruct 70BOpenMeta35.4———
10NewGemma 3 12B InstructOpenGoogle33.8———
11▼ 3Llama 3.2 Instruct 90B (Vision)OpenMeta33.4———
12▼ 3Llama 3 Instruct 70BOpenMeta27.5———
13▼ 3Phi-4 Multimodal InstructOpenMicrosoft Azure26.9———
14▼ 3Phi-4 Mini InstructOpenMicrosoft Azure26.0———
15▼ 3Phi-3 Medium Instruct 14BOpenMicrosoft Azure24.5———
16NewGemma 3 4B InstructOpenGoogle24.5———
17▼ 4Llama 3.1 Instruct 8BOpenMeta23.7———
18▼ 4Gemma 2 9BOpenGoogle22.2———
19▼ 4Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure22.1———
20▼ 4Llama 3 Instruct 8BOpenMeta21.5———
21▼ 4Llama 2 Chat 13BOpenMeta19.9———
22▼ 4DBRX InstructOpenDatabricks19.8———
23▼ 4Llama 3.2 Instruct 3BOpenMeta19.5———
24▼ 4Llama 3.2 Instruct 1BOpenMeta9.7———
25▼ 4Llama 2 Chat 7BOpenMeta8.3———

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 “—”.