Skip to content
IFAI

Model rankings

1278 models · 5 boards · 2 sources

‹
Week of June 15, 2026
July 27, 202639 changesJuly 20, 202618 changesJuly 13, 202611 changesJuly 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 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated June 19, 2026

Smartest
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic59.9Intelligence
Best open model
GLM-5.2 (max)Z AI51.1Intelligence
Best value
HyperNova 60B 2605Multiverse Computing341 pts/$Value
Best from China
GLM-5.2 (max)Z AI51.1Intelligence
Top three by Intelligence
1Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic59.9
2Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic55.7
3GPT-5.5 (xhigh)OpenAI54.8
Top three open models
1GLM-5.2 (max)Z AI · #6 overall51.1
2MiniMax-M3MiniMax · #11 overall44.4
3DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #12 overall44.3
This week's changes
glm-5.2 (max)Coding · #2New
GLM-5.2 (max)Intelligence · #6New
seed-2.1-pro-previewCoding · #6New
Lightning V3.1 Pro TTS (Jun 2026)Speech · #11New
kimi-k2.7-codeCoding · #17New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic59.9$20——
2—Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic55.7$105921 s
3—GPT-5.5 (xhigh)ClosedOpenAI54.8$115684 s
4▲ 1Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.5$105318 s
5▼ 1GPT-5.5 (high)ClosedOpenAI53.1$115640 s
6▲ 1GPT-5.4 (xhigh)ClosedOpenAI51.4$5.6146115 s
7▲ 2Gemini 3.5 Flash (high)ClosedGoogle50.2$3.416118 s
8▲ 8Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic47.2$6.057106 s
9▼ 1GPT-5.5 (medium)ClosedOpenAI47.1$115210 s
10▼ 4Gemini 3.1 Pro PreviewClosedGoogle46.5$4.512319 s
11▼ 1Gemini 3.5 Flash (medium)ClosedGoogle45.4$3.416217 s
12▼ 1GPT-5.3 Codex (xhigh)ClosedOpenAI44.3$4.87287 s
13—Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic43.7$104420 s
14—Muse SparkClosedMeta43.1———
15—Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic42.7$10461.2 s
16▲ 1GPT-5.2 (xhigh)ClosedOpenAI42.2$4.870133 s
17▲ 1GPT-5.5 (low)ClosedOpenAI41.7$11531.7 s
18▲ 1Claude Opus 4.5 (Reasoning)ClosedAnthropic40.8$105514 s
19▲ 2GPT-5.2 Codex (xhigh)ClosedOpenAI40.1$4.813838 s
20▲ 2GPT-5.4 mini (xhigh)ClosedOpenAI40.0$1.71758.6 s
21▲ 4Gemini 3 Pro Preview (high)ClosedGoogle39.6$4.5——
22▲ 4GPT-5.4 (low)ClosedOpenAI39.1$5.9951.6 s
23▲ 4GPT-5.1 (high)ClosedOpenAI38.9$3.49343 s
24▲ 11GPT-5.4 nano (xhigh)ClosedOpenAI38.2$0.461575.0 s
25▲ 4GPT-5.2 (medium)ClosedOpenAI38.0$4.8——
26▲ 4Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic37.8$10402.3 s
27▲ 1Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA37.8$1.21701.1 s
28▲ 3Gemini 3 Flash Preview (Reasoning)ClosedGoogle37.8$1.11666.9 s
29▼ 17Grok 4.3 (high)ClosedxAI37.6$1.615211 s
30▼ 10Grok 4.20 0309 v2 (Reasoning)ClosedxAI37.0$3.014813 s
31▼ 7Grok 4.20 0309 (Reasoning)ClosedxAI36.5$3.015613 s
32—GPT-5 Codex (high)ClosedOpenAI36.1$3.416616 s
33—GPT-5 (high)ClosedOpenAI36.1$3.49283 s
34▼ 11Grok 4.3 (medium)ClosedxAI36.0$1.61558.2 s
35▼ 1Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic35.9$6.0441.2 s
36—Grok 4.3 (low)ClosedxAI35.4$1.61223.8 s
37—Gemini 3.5 Flash (minimal)ClosedGoogle34.9$3.41630.9 s
38—GPT-5.1 Codex (high)ClosedOpenAI34.7$3.41717.7 s
39—Claude Opus 4.5 (Non-reasoning)ClosedAnthropic34.7$10491.6 s
40—Claude 4.5 Sonnet (Reasoning)ClosedAnthropic34.7$6.05015 s
41—Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic34.3$6.0441.3 s
42—GPT-5 (medium)ClosedOpenAI33.7$3.48240 s
43—Claude 4.1 Opus (Reasoning)ClosedAnthropic33.7$303415 s
44—GPT-5.5 Instant (May 2026)ClosedOpenAI33.5$11——
45—Grok 4ClosedxAI33.3$11——
46—Gemini 3 Pro Preview (low)ClosedGoogle33.1$4.5——
47—GPT-5 mini (high)ClosedOpenAI33.0$0.699682 s
48—GPT-5.5 (Non-reasoning)ClosedOpenAI32.7$11551.0 s
49—o3-proClosedOpenAI32.5$353563 s
50—GPT-5 (low)ClosedOpenAI31.2$3.4799.3 s

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 “—”.