Skip to content
IFAI

Model rankings

428 models · 2 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated July 7, 2025

Smartest
o3-proOpenAI71.0Intelligence
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
1o3-proOpenAI71.0
2Gemini 2.5 ProGoogle70.5
3o3OpenAI70.0
Top three open models
1DeepSeek R1 0528 (May '25)DeepSeek · #6 overall68.3
2MiniMax M1 80kMiniMax · #11 overall63.0
3Qwen3 235B A22B (Reasoning)Alibaba · #12 overall62.3
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—DeepSeek R1 0528 (May '25)OpenDeepSeek68.3$0.96——
2—MiniMax M1 80kOpenMiniMax63.0$0.83——
3—Qwen3 235B A22B (Reasoning)OpenAlibaba62.3$2.6——
4—MiniMax M1 40kOpenMiniMax61.4$0.83——
5—DeepSeek R1 (Jan '25)OpenDeepSeek60.2$2.0——
6—Qwen3 32B (Reasoning)OpenAlibaba59.2$2.6——
7—QwQ 32BOpenAlibaba58.1$0.33——
8—Qwen3 14B (Reasoning)OpenAlibaba55.7$1.3——
9—Qwen3 30B A3B (Reasoning)OpenAlibaba55.6$0.75——
10—DeepSeek V3 0324 (Mar '25)OpenDeepSeek53.2$0.48——
11—DeepSeek R1 0528 Qwen3 8BOpenDeepSeek52.2$0.065——
12—DeepSeek R1 Distill Qwen 32BOpenDeepSeek51.9$0.30——
13—Qwen3 8B (Reasoning)OpenAlibaba51.4$0.66——
14—DeepSeek R1 Distill Qwen 14BOpenDeepSeek49.0$0.20——
15—DeepSeek R1 Distill Llama 70BOpenDeepSeek48.2$0.72——
16—Qwen3 4B (Reasoning)OpenAlibaba47.3$0.40——
17—Qwen3 235B A22BOpenAlibaba47.1$1.2——
18—DeepSeek V3 (Dec '24)OpenDeepSeek45.6$0.48——
19—Qwen2.5 MaxClosedAlibaba45.3$2.8——
20—Qwen3 32BOpenAlibaba43.5$1.2——
21—QwQ 32B-PreviewOpenAlibaba42.6$0.67——
22—Qwen3 30B A3BOpenAlibaba42.6$0.35——
23—Qwen3 14BOpenAlibaba41.0$0.61——
24—Qwen2.5 Instruct 72BOpenAlibaba40.4$0.000——
25—MiniMax-Text-01OpenMiniMax40.2$0.43——
26—Qwen3 1.7B (Reasoning)OpenAlibaba38.2$0.40——
27—Qwen2.5 Instruct 32BOpenAlibaba37.4$0.15——
28—Qwen3 8BOpenAlibaba36.7$0.31——
29—Qwen2.5 Coder Instruct 32BOpenAlibaba36.3$0.15——
30—DeepSeek-V2.5 (Dec '24)OpenDeepSeek35.3$0.18——
31—Qwen3 4BOpenAlibaba35.2$0.19——
32—DeepSeek-V2.5OpenDeepSeek34.7$0.18——
33—DeepSeek R1 Distill Llama 8BOpenDeepSeek34.0$0.040——
34—Qwen2.5 TurboClosedAlibaba33.6$0.088——
35—Qwen2 Instruct 72BOpenAlibaba32.6$0.000——
36—DeepSeek-Coder-V2OpenDeepSeek29.0$0.18——
37—Yi-LargeClosed01.AI27.9$0.000——
38—Qwen2.5 Coder Instruct 7BOpenAlibaba26.7$0.000——
39—Qwen3 1.7BOpenAlibaba25.0$0.19——
40—Qwen1.5 Chat 110BOpenAlibaba25.0$0.000——
41—Qwen3 0.6B (Reasoning)OpenAlibaba23.2$0.40——
42—DeepSeek-V2-ChatOpenDeepSeek23.0$0.18——
43—Qwen Chat 72BOpenAlibaba22.0$1.0——
44—DeepSeek Coder V2 Lite InstructOpenDeepSeek20.5$0.000——
45—DeepSeek LLM 67B Chat (V1)OpenDeepSeek20.0$0.000——
46—DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek19.2$0.000——
47—Qwen3 0.6BOpenAlibaba16.7$0.19——
48—Qwen Chat 14BOpenAlibaba14.0$0.000——

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 “—”.