Skip to content
IFAI

Model rankings

569 models · 3 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated September 30, 2025

Smartest
GPT-5 (high)OpenAI68.5Intelligence
Best open model
gpt-oss-120B (high)OpenAI58.0Intelligence
Best value
Gemma 3n E4B InstructGoogle620 pts/$Value
Best from China
DeepSeek V3.1 Terminus (Reasoning)DeepSeek57.7Intelligence
Top three by Intelligence
1GPT-5 (high)OpenAI68.5
2GPT-5 Codex (high)OpenAI67.6
3o3OpenAI65.5
Top three open models
1gpt-oss-120B (high)OpenAI · #12 overall58.0
2DeepSeek V3.1 Terminus (Reasoning)DeepSeek · #13 overall57.7
3Qwen3 235B A22B 2507 (Reasoning)Alibaba · #14 overall57.5
This week's changes
GPT-5 Codex (high)Intelligence · #2New
Claude 4.5 Sonnet (Reasoning)Intelligence · #7New
DeepSeek V3.1 Terminus (Reasoning)Intelligence · #13New
Qwen3 235B A22B 2507 InstructIntelligence · #39New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—gpt-oss-120B (high)OpenOpenAI58.0$0.26——
2NewDeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek57.7$0.84——
3▼ 1Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba57.5$2.6——
4▼ 1Qwen3 Next 80B A3B (Reasoning)OpenAlibaba54.3$1.9——
5▼ 1DeepSeek V3.1 (Reasoning)OpenDeepSeek54.0$0.65——
6▼ 1DeepSeek R1 0528 (May '25)OpenDeepSeek52.0$1.4——
7▼ 1Kimi K2 0905OpenMoonshot AI50.4$1.4——
8▼ 1GLM-4.5OpenZ AI49.4$0.99——
9▼ 1GLM-4.5-AirOpenZ AI48.8$0.43——
10▼ 1Kimi K2OpenMoonshot AI48.2$1.1——
11▼ 1Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba46.4$0.75——
12▼ 1MiniMax M1 80kOpenMiniMax46.2$0.83——
13NewDeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek45.7$0.84——
14NewQwen3 235B A22B 2507 InstructOpenAlibaba45.3$1.2——
15▼ 2Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA45.2$0.18——
16NewQwen3 Next 80B A3B InstructOpenAlibaba44.8$0.88——
17▼ 2DeepSeek V3.1 (Non-reasoning)OpenDeepSeek44.8$0.86——
18▼ 1DeepSeek R1 (Jan '25)OpenDeepSeek43.8$1.8——
19▼ 1Qwen3 4B 2507 (Reasoning)OpenAlibaba43.4$0.000——
20▼ 5gpt-oss-20B (high)OpenOpenAI43.3$0.088——
21▼ 2Magistral Small 1.2OpenMistral43.0$0.75——
22▼ 2EXAONE 4.0 32B (Reasoning)OpenLG AI Research42.6$0.70——
23NewQwen3 Coder 480B A35B InstructOpenAlibaba42.3$3.0——
24▼ 2Qwen3 235B A22B (Reasoning)OpenAlibaba41.7$2.6——
25▼ 2MiniMax M1 40kOpenMiniMax41.6$0.83——
26▼ 2Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research41.6$1.5——
27▼ 2DeepSeek V3 0324OpenDeepSeek41.3$0.99——
28NewQwen3 Omni 30B A3B (Reasoning)OpenAlibaba40.0$0.000——
29▼ 3Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research39.2$0.20——
30▼ 3Qwen3 32B (Reasoning)OpenAlibaba38.7$2.6——
31▼ 3Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA38.5$0.90——
32▼ 2QwQ 32BOpenAlibaba37.9$0.44——
33▼ 2GLM-4.5V (Reasoning)OpenZ AI37.0$0.85——
34NewQwen3 30B A3B 2507 InstructOpenAlibaba37.0$0.35——
35▼ 2NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA36.9$0.070——
36▼ 2Qwen3 30B A3B (Reasoning)OpenAlibaba36.7$0.75——
37NewNVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA36.1$0.070——
38▼ 3Qwen3 14B (Reasoning)OpenAlibaba36.0$1.3——
39▼ 3Llama 4 MaverickOpenMeta35.8$0.39——
40▼ 3Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA35.5$0.000——
41▼ 3DeepSeek R1 0528 Qwen3 8BOpenDeepSeek34.8$0.065——
42NewQwen3 Coder 30B A3B InstructOpenAlibaba33.4$0.90——
43▼ 2DeepSeek R1 Distill Qwen 32BOpenDeepSeek32.7$0.29——
44NewHermes 4 - Llama-3.1 405B (Non-reasoning)OpenNous Research32.6$1.5——
45▼ 2Reka Flash 3OpenReka AI32.5$0.35——
46▼ 2DeepSeek V3 (Dec '24)OpenDeepSeek32.5$0.69——
47▼ 2Magistral Small 1OpenMistral31.9$0.75——
48▼ 2DeepSeek R1 Distill Llama 70BOpenDeepSeek30.8$0.77——
49NewEXAONE 4.0 32B (Non-reasoning)OpenLG AI Research30.3$0.70——
50NewQwen3 Omni 30B A3B InstructOpenAlibaba30.2$0.43——

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 “—”.