Skip to content
IFAI

Model rankings

539 models · 3 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated September 23, 2025

Smartest
GPT-5 (high)OpenAI66.7Intelligence
Best open model
gpt-oss-120B (high)OpenAI57.9Intelligence
Best value
Gemma 3n E4B InstructGoogle624 pts/$Value
Best from China
Qwen3 235B A22B 2507 (Reasoning)Alibaba57.5Intelligence
Top three by Intelligence
1GPT-5 (high)OpenAI66.7
2Grok 4xAI65.3
3o3-proOpenAI65.3
Top three open models
1gpt-oss-120B (high)OpenAI · #10 overall57.9
2Qwen3 235B A22B 2507 (Reasoning)Alibaba · #11 overall57.5
3Qwen3 Next 80B A3B (Reasoning)Alibaba · #14 overall54.3
This week's changes
Grok 4 Fast (Reasoning)Intelligence · #6New
Magistral Medium 1.2Intelligence · #18New
Magistral Small 1.2Intelligence · #39New
Magistral Medium 1Intelligence · #69New
Magistral Small 1Intelligence · #73New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 3 more variants57.5$2.6——
2—Qwen3 Next 80B A3B (Reasoning)OpenAlibaba · 1 more variant54.3$1.9——
3—DeepSeek V3.1 (Reasoning)OpenDeepSeek · 1 more variant54.0$0.45——
4—DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant52.0$1.4——
5—Kimi K2 0905OpenMoonshot AI · 1 more variant50.4$1.4——
6—GLM-4.5OpenZ AI49.4$0.99——
7—GLM-4.5-AirOpenZ AI48.8$0.43——
8—Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 3 more variants46.4$0.75——
9—MiniMax M1 80kOpenMiniMax46.2$0.83——
10—Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants43.4$0.000——
11—Qwen3 Coder 480B A35BOpenAlibaba42.3$3.0——
12—MiniMax M1 40kOpenMiniMax41.6$0.83——
13—DeepSeek V3 0324OpenDeepSeek · 1 more variant41.3$0.99——
14—Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant38.7$2.6——
15—QwQ 32BOpenAlibaba37.9$0.44——
16—GLM-4.5V (Reasoning)OpenZ AI · 1 more variant37.0$0.85——
17—Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant36.0$1.3——
18—DeepSeek R1 0528 Qwen3 8BOpenDeepSeek34.8$0.065——
19—Qwen3 Coder 30B A3BOpenAlibaba33.4$0.90——
20—DeepSeek R1 Distill Qwen 32BOpenDeepSeek32.7$0.29——
21—DeepSeek R1 Distill Llama 70BOpenDeepSeek30.8$0.77——
22—DeepSeek R1 Distill Qwen 14BOpenDeepSeek29.7$0.88——
23▲ 2Qwen2.5 Instruct 72BOpenAlibaba29.0$0.000——
24▼ 1Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant28.3$0.66——
25▼ 1QwQ 32B-PreviewOpenAlibaba28.0$0.67——
26—MiniMax-Text-01OpenMiniMax25.7$0.43——
27—Qwen2.5 Instruct 32BOpenAlibaba22.9$0.000——
28—Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant22.4$0.40——
29—Qwen2.5 Coder Instruct 32BOpenAlibaba21.8$0.20——
30—DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant20.7$0.000——
31—DeepSeek R1 Distill Llama 8BOpenDeepSeek19.5$0.040——
32—Qwen2 Instruct 72BOpenAlibaba18.1$0.000——
33—DeepSeek-Coder-V2OpenDeepSeek14.5$0.000——
34—Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant14.2$0.40——
35—Qwen2.5 Coder Instruct 7BOpenAlibaba12.2$0.000——
36—Qwen1.5 Chat 110BOpenAlibaba10.5$0.000——
37—DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek8.6$0.000——
38—DeepSeek-V2-ChatOpenDeepSeek8.6$0.000——
39—Qwen Chat 72BOpenAlibaba7.6$1.0——
40—DeepSeek Coder V2 Lite InstructOpenDeepSeek6.1$0.000——
41—DeepSeek LLM 67B Chat (V1)OpenDeepSeek5.6$0.000——
42—Qwen Chat 14BOpenAlibaba1.0$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 “—”.