Skip to content
IFAI

Model rankings

716 models · 4 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated October 21, 2025

Smartest
GPT-5 Codex (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 Codex (high)OpenAI68.5
2GPT-5 (high)OpenAI68.5
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
Magpie MultilingualSpeech · #17Up 11
Octave 2Speech · #20Up 5
Sonic English (Oct '24)Speech · #21Up 3
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek57.7$1.9——
2—Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba57.5$2.6——
3—DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek56.9$0.32——
4—GLM-4.6 (Reasoning)OpenZ AI56.0$0.98——
5—Qwen3 MaxClosedAlibaba55.2$2.4——
6—Qwen3 Next 80B A3B (Reasoning)OpenAlibaba54.3$1.9——
7—DeepSeek V3.1 (Reasoning)OpenDeepSeek54.0$0.65——
8—DeepSeek R1 0528 (May '25)OpenDeepSeek52.0$1.7——
9—Seed-OSS-36B-InstructOpenByteDance Seed51.6$0.30——
10—GLM-4.5 (Reasoning)OpenZ AI51.3$0.98——
11—Kimi K2 0905OpenMoonshot AI50.4$1.4——
12—GLM-4.5-AirOpenZ AI48.8$0.43——
13—Qwen3 Max (Preview)ClosedAlibaba48.6$2.4——
14—Kimi K2OpenMoonshot AI48.2$1.1——
15—Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba46.4$0.75——
16—DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek46.3$0.32——
17—MiniMax M1 80kOpenMiniMax46.2$0.83——
18—DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek45.7$0.45——
19—Qwen3 235B A22B 2507 InstructOpenAlibaba45.3$1.2——
20—Qwen3 Next 80B A3B InstructOpenAlibaba44.8$0.88——
21—DeepSeek V3.1 (Non-reasoning)OpenDeepSeek44.8$0.84——
22—GLM-4.6 (Non-reasoning)OpenZ AI44.7$0.98——
23—DeepSeek R1 (Jan '25)OpenDeepSeek43.8$1.8——
24—Qwen3 4B 2507 (Reasoning)OpenAlibaba43.4$0.000——
25—Qwen3 Coder 480B A35B InstructOpenAlibaba42.3$3.0——
26—Qwen3 235B A22B (Reasoning)OpenAlibaba41.7$2.6——
27—DeepSeek V3 0324OpenDeepSeek41.3$0.99——
28—MiniMax M1 40kOpenMiniMax40.0$0.83——
29—Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba40.0$0.43——
30—Qwen3 32B (Reasoning)OpenAlibaba38.7$2.6——
31—QwQ 32BOpenAlibaba37.9$0.44——
32—GLM-4.5V (Reasoning)OpenZ AI37.0$0.90——
33—Qwen3 30B A3B 2507 InstructOpenAlibaba37.0$0.35——
34—Qwen3 30B A3B (Reasoning)OpenAlibaba36.7$0.75——
35—Qwen3 14B (Reasoning)OpenAlibaba36.0$1.3——
36—Qwen3 Coder 30B A3B InstructOpenAlibaba33.4$0.90——
37—ERNIE 4.5 300B A47BOpenBaidu32.9$0.49——
38—DeepSeek R1 Distill Qwen 32BOpenDeepSeek32.7$0.29——
39—DeepSeek V3 (Dec '24)OpenDeepSeek32.5$0.61——
40—DeepSeek R1 0528 Qwen3 8BOpenDeepSeek31.0$0.065——
41—Qwen2.5 MaxClosedAlibaba30.7$2.8——
42—Qwen3 4B 2507 InstructOpenAlibaba30.4$0.000——
43—Qwen3 Omni 30B A3B InstructOpenAlibaba30.2$0.43——
44—Qwen3 235B A22B (Non-reasoning)OpenAlibaba30.0$1.2——
45—DeepSeek R1 Distill Llama 70BOpenDeepSeek29.9$0.77——
46—DeepSeek R1 Distill Qwen 14BOpenDeepSeek29.7$0.88——
47—Qwen3 14B (Non-reasoning)OpenAlibaba29.2$0.61——
48—Qwen2.5 Instruct 72BOpenAlibaba29.0$0.000——
49—MiniMax-Text-01OpenMiniMax28.3$0.43——
50—Qwen3 8B (Reasoning)OpenAlibaba28.3$0.66——

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 “—”.