Skip to content
IFAI

Model rankings

1239 models · 5 boards · 2 sources

‹
Week of May 25, 2026
July 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changesJune 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changesMay 25, 202617 changesMay 18, 202616 changesMay 11, 202665 changesMay 4, 202616 changesApril 27, 202624 changesApril 20, 202627 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated May 29, 2026

Smartest
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic61.4Intelligence
Best open model
Kimi K2.6Kimi53.9Intelligence
Best value
Qwen3.5 0.8B (Reasoning)Alibaba526 pts/$Value
Best from China
Qwen3.7 MaxAlibaba56.6Intelligence
Top three by Intelligence
1Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic61.4
2GPT-5.5 (xhigh)OpenAI60.2
3Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic57.3
Top three open models
1Kimi K2.6Kimi · #8 overall53.9
2MiMo-V2.5-ProXiaomi · #9 overall53.8
3DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #16 overall51.5
This week's changes
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Intelligence · #1New
qwen3.7-max-20260517Coding · #3New
xAI Text to SpeechSpeech · #5New
Recraft V4.1 Utility ProImage · #6New
Fun-Realtime-TTS-PreviewSpeech · #6New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1NewClaude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic61.4$116420 s
2▼ 1GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants60.2$116064 s
3▼ 1Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant57.3$115516 s
4▼ 1Gemini 3.1 Pro PreviewClosedGoogle57.2$4.513322 s
5▼ 1GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants56.8$5.684157 s
6▼ 1Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants55.3$3.420617 s
7▼ 1GPT-5.3 Codex (xhigh)ClosedOpenAI53.6$4.874125 s
8▼ 1Grok 4.3 (high)ClosedxAI · 3 more variants53.2$1.617612 s
9▼ 1Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant52.9$114215 s
10▼ 1Muse SparkClosedMeta52.2———
11▼ 1Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants51.7$6.661111 s
12▼ 1GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants51.3$4.872122 s
13▼ 1Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant49.7$114817 s
14▼ 1Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant49.3$3.018513 s
15▼ 1GPT-5.2 Codex (xhigh)ClosedOpenAI49.0$4.810526 s
16▼ 1GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants48.9$1.71527.5 s
17▼ 1Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant48.5$3.018711 s
18▼ 1Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant48.4$4.513544 s
19▼ 1GPT-5.1 (high)ClosedOpenAI · 1 more variant47.7$3.49737 s
20▼ 1Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant46.4$1.11737.5 s
21▼ 1GPT-5 Codex (high)ClosedOpenAI44.6$3.41897.9 s
22▼ 1GPT-5 (high)ClosedOpenAI · 4 more variants44.6$3.48876 s
23▼ 1GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants44.0$0.461424.2 s
24▼ 1GPT-5.1 Codex (high)ClosedOpenAI43.1$3.41786.4 s
25▼ 1Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant43.0$6.64211 s
26▼ 1Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant42.0$333014 s
27NewGPT-5.5 Instant (May 2026)ClosedOpenAI41.8$11——
28▼ 2Grok 4ClosedxAI41.5$11——
29▼ 2GPT-5 mini (high)ClosedOpenAI · 2 more variants41.2$0.698894 s
30▼ 2o3-proClosedOpenAI40.7$352991 s
31▼ 2Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant39.0$33308.3 s
32▼ 2Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant38.7$6.64213 s
33▼ 2GPT-5.1 Codex mini (high)ClosedOpenAI38.6$0.691716.2 s
34▼ 2Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant38.6———
35▼ 2o3ClosedOpenAI38.4$3.51106.3 s
36▼ 2Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant37.1$2.29717 s
37▼ 2Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants35.7$3.411912 s
38▼ 2Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant35.1$0.28——
39▼ 2Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant34.7———
40▼ 2Gemini 2.5 ProClosedGoogle34.6$3.413722 s
41▼ 2Nova 2.0 Lite (high)ClosedAmazon · 3 more variants34.5$0.8516615 s
42NewGemini 3.1 Flash-LiteClosedGoogle33.5$0.562795.7 s
43▼ 2o4-mini (high)ClosedOpenAI33.1$1.914225 s
44▼ 2Mercury 2ClosedInception32.8$0.388253.0 s
45▼ 2Grok 3 mini Reasoning (high)ClosedxAI32.1$0.35880.6 s
46▼ 2Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants31.1———
47▼ 2o1ClosedOpenAI · 1 more variant30.7$268031 s
48▼ 2Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant30.3———
49▼ 2Grok Code Fast 1ClosedxAI28.7———
50▼ 2Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants28.0$0.85——

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 “—”.