Skip to content
IFAI

Model rankings

443 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated July 16, 2025

Smartest
Grok 4xAI73.2Intelligence
Best open model
DeepSeek R1 0528 (May '25)DeepSeek68.3Intelligence
Best value
Gemma 3n E4B InstructGoogle1,120 pts/$Value
Best from China
DeepSeek R1 0528 (May '25)DeepSeek68.3Intelligence
Top three by Intelligence
1Grok 4xAI73.2
2o3-proOpenAI71.0
3Gemini 2.5 ProGoogle70.5
Top three open models
1DeepSeek R1 0528 (May '25)DeepSeek · #7 overall68.3
2MiniMax M1 80kMiniMax · #12 overall63.0
3Qwen3 235B A22B (Reasoning)Alibaba · #13 overall62.3
This week's changes
Grok 4Intelligence · #1New
Kimi k2Intelligence · #22New
Devstral MediumIntelligence · #75New
Devstral Small (May '25)Intelligence · #92New
Grok-1Intelligence · #103New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewGrok 4ClosedxAI73.2$6.0——
2▼ 1o3-proClosedOpenAI71.0$35——
3▼ 1Gemini 2.5 ProClosedGoogle70.5$3.4——
4▼ 1o3ClosedOpenAI70.0$3.5——
5▼ 1o4-mini (high)ClosedOpenAI69.8$1.9——
6▼ 1Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant68.9$3.4——
7▼ 1DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant68.3$0.96——
8▼ 1Grok 3 mini Reasoning (high)ClosedxAI66.7$0.35——
9▼ 1o3-mini (high)ClosedOpenAI · 1 more variant65.5$1.9——
10▼ 1Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant65.1$0.99——
11▼ 1Claude 4 Opus (Extended Thinking)ClosedAnthropic · 1 more variant64.4$30——
12▼ 1MiniMax M1 80kOpenMiniMax63.0$0.83——
13▼ 1Qwen3 235B A22B (Reasoning)OpenAlibaba · 1 more variant62.3$2.6——
14▼ 1o1ClosedOpenAI · 1 more variant61.9$26——
15▼ 1MiniMax M1 40kOpenMiniMax61.4$0.83——
16▼ 1Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA60.8$0.90——
17▼ 1Claude 4 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant60.8$6.0——
18▼ 1Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle · 1 more variant60.5$0.99——
19▼ 1Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant59.2$2.6——
20▲ 18Solar Pro 2 (Reasoning)ClosedUpstage · 3 more variants58.2$0.50——
21▼ 2QwQ 32BOpenAlibaba58.1$0.33——
22NewKimi k2OpenMoonshot AI57.5$1.5——
23▼ 3Claude 3.7 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant57.4$6.0——
24▼ 3Grok 3 Reasoning BetaClosedxAI56.1$0.000——
24▼ 3o1-proClosedOpenAI56.1$263——
26▼ 3Magistral MediumClosedMistral56.0$2.8——
27▼ 3Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant55.7$1.3——
28▼ 3Qwen3 30B A3B (Reasoning)OpenAlibaba · 1 more variant55.6$0.75——
29▼ 3Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant54.9$0.18——
30▼ 3Magistral SmallOpenMistral54.7$0.75——
31▼ 3o1-miniClosedOpenAI53.8$1.9——
32▼ 3DeepSeek V3 0324 (Mar '25)OpenDeepSeek · 1 more variant53.2$0.48——
33▼ 3GPT-4.5 (Preview)ClosedOpenAI53.0$94——
34▼ 3GPT-4.1 miniClosedOpenAI52.9$0.70——
35▼ 3GPT-4.1ClosedOpenAI52.6$3.5——
36▼ 3Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant52.3$0.000——
37▼ 3DeepSeek R1 0528 Qwen3 8BOpenDeepSeek52.2$0.065——
38▼ 3DeepSeek R1 Distill Qwen 32BOpenDeepSeek51.9$0.30——
39▼ 3Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant51.4$0.66——
40▼ 3Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant51.2$0.000——
41▼ 2Grok 3ClosedxAI50.6$6.0——
42▼ 2Llama 4 MaverickOpenMeta50.5$0.39——
43▼ 2GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants50.3$7.5——
44▼ 2Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle49.2$0.000——
45▼ 2DeepSeek R1 Distill Qwen 14BOpenDeepSeek49.0$0.20——
46▼ 2Mistral Medium 3ClosedMistral49.0$0.80——
47▼ 2Sonar ReasoningClosedPerplexity48.8$2.0——
48▼ 2DeepSeek R1 Distill Llama 70BOpenDeepSeek48.2$0.72——
49▼ 2Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant48.1$0.18——
50▼ 2Qwen3 4B (Reasoning)OpenAlibaba · 1 more variant47.3$0.40——

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 “—”.