Skip to content
IFAI

Model rankings

517 models · 3 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated August 26, 2025

Smartest
GPT-5 (high)OpenAI69.0Intelligence
Best open model
Qwen3 235B A22B 2507 (Reasoning)Alibaba63.6Intelligence
Best value
Gemma 3n E4B InstructGoogle739 pts/$Value
Best from China
Qwen3 235B A22B 2507 (Reasoning)Alibaba63.6Intelligence
Top three by Intelligence
1GPT-5 (high)OpenAI69.0
2Grok 4xAI67.5
3o3-proOpenAI67.5
Top three open models
1Qwen3 235B A22B 2507 (Reasoning)Alibaba · #8 overall63.6
2gpt-oss-120BOpenAI · #9 overall61.3
3DeepSeek V3.1 (Reasoning)DeepSeek · #11 overall59.7
This week's changes
DeepSeek V3.1 (Reasoning)Intelligence · #11New
GLM-4.5V (Reasoning)Intelligence · #45New
LFM2 1.2BIntelligence · #164New
Llama 3.2 Instruct 3BIntelligence · #152Up 26
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba63.6$2.6——
2NewDeepSeek V3.1 (Reasoning)OpenDeepSeek59.7$0.96——
3▼ 1DeepSeek R1 0528 (May '25)OpenDeepSeek58.6$0.96——
4▼ 1GLM-4.5OpenZ AI56.1$0.99——
5▼ 1Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba53.9$0.75——
6▼ 1MiniMax M1 80kOpenMiniMax53.2$0.83——
7▲ 2GLM-4.5-AirOpenZ AI52.8$0.43——
8—DeepSeek R1 (Jan '25)OpenDeepSeek52.7$1.8——
9▼ 2Qwen3 235B A22B 2507 (Non-reasoning)OpenAlibaba50.7$1.2——
10NewDeepSeek V3.1 (Non-reasoning)OpenDeepSeek48.8$0.48——
11▼ 1Kimi K2OpenMoonshot AI48.6$1.1——
12▼ 1Qwen3 235B A22B (Reasoning)OpenAlibaba48.4$2.6——
13▼ 7MiniMax M1 40kOpenMiniMax45.8$0.83——
14—Qwen3 Coder 480B A35BOpenAlibaba45.2$3.0——
15▼ 2Qwen3 30B A3B 2507 (Non-reasoning)OpenAlibaba44.3$0.35——
16▼ 1Qwen3 32B (Reasoning)OpenAlibaba44.3$2.6——
17▼ 1DeepSeek V3 0324 (Mar '25)OpenDeepSeek44.0$0.48——
18NewGLM-4.5V (Reasoning)OpenZ AI42.9$0.000——
19▼ 2Qwen3 30B A3B (Reasoning)OpenAlibaba42.3$0.75——
20▼ 8QwQ 32BOpenAlibaba41.9$0.63——
21▼ 1Qwen3 8B (Reasoning)OpenAlibaba40.8$0.66——
22▼ 1Qwen3 14B (Reasoning)OpenAlibaba40.3$1.3——
23▼ 5DeepSeek R1 0528 Qwen3 8BOpenDeepSeek38.6$0.065——
24▲ 1DeepSeek V3 (Dec '24)OpenDeepSeek36.9$0.48——
25▼ 6DeepSeek R1 Distill Qwen 32BOpenDeepSeek36.4$0.20——
26▲ 1Qwen3 Coder 30B A3BOpenAlibaba35.6$0.90——
27▼ 4DeepSeek R1 Distill Llama 70BOpenDeepSeek34.5$0.77——
28▼ 2Qwen2.5 MaxClosedAlibaba34.3$2.8——
29▼ 1Qwen3 235B A22BOpenAlibaba33.3$1.2——
30▼ 8DeepSeek R1 Distill Qwen 14BOpenDeepSeek33.3$0.88——
31—Qwen3 14BOpenAlibaba31.9$0.61——
32▼ 3QwQ 32B-PreviewOpenAlibaba31.5$0.67——
33—Qwen2.5 Instruct 72BOpenAlibaba31.4$0.000——
34▼ 4Qwen3 30B A3BOpenAlibaba29.9$0.35——
35▼ 3Qwen3 32BOpenAlibaba29.8$1.2——
36▼ 2MiniMax-Text-01OpenMiniMax29.1$0.43——
37▼ 13Qwen3 4B (Reasoning)OpenAlibaba29.0$0.40——
38▼ 3Qwen3 1.7B (Reasoning)OpenAlibaba26.9$0.40——
39▼ 3Qwen2.5 Instruct 32BOpenAlibaba26.1$0.15——
40▼ 3Qwen3 8BOpenAlibaba25.4$0.31——
41▼ 3Qwen2.5 Coder Instruct 32BOpenAlibaba25.0$0.15——
42▼ 3DeepSeek-V2.5 (Dec '24)OpenDeepSeek23.9$0.18——
43▼ 3Qwen3 4BOpenAlibaba23.8$0.19——
44▼ 3DeepSeek-V2.5OpenDeepSeek23.3$0.18——
45▼ 3DeepSeek R1 Distill Llama 8BOpenDeepSeek22.8$0.040——
46▼ 3Qwen2.5 TurboClosedAlibaba22.1$0.088——
47▼ 3Qwen2 Instruct 72BOpenAlibaba21.1$0.000——
48▼ 3DeepSeek-Coder-V2OpenDeepSeek17.3$0.18——
49▼ 3Yi-LargeClosed01.AI16.2$0.000——
50▼ 3Qwen2.5 Coder Instruct 7BOpenAlibaba14.9$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 “—”.