Skip to content
IFAI

Model rankings

1371 models · 5 boards · 2 sources

‹
Week of July 20, 2026
August 31, 202620 changesAugust 24, 202615 changesAugust 17, 202633 changesAugust 10, 2026116 changesAugust 3, 202613 changesJuly 27, 202639 changesJuly 20, 202618 changesJuly 13, 202611 changesJuly 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changesJune 15, 2026184 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated July 20, 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
Qwen3.5 4B (Reasoning)Alibaba335 pts/$Value
Best from China
Kimi K3Kimi57.1Intelligence
Top three by Intelligence
1Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic59.9
2GPT-5.6 Sol (max)OpenAI58.9
3Kimi K3Kimi57.1
Top three open models
1GLM-5.2 (max)Z AI · #12 overall51.1
2MiniMax-M3MiniMax · #18 overall44.4
3DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #19 overall44.3
This week's changes
kimi-k3-maxCoding · #1New
claude-opus-5-highCoding · #2New
Kimi K3Intelligence · #3New
glm-5.2-maxCoding · #5New
gemini-3.6-flashCoding · #13New
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$2061113 s
2—GPT-5.6 Sol (max)ClosedOpenAI58.9$1162128 s
3—GPT-5.6 Sol (xhigh)ClosedOpenAI57.7$116042 s
4—GPT-5.6 Sol (high)ClosedOpenAI55.9$115913 s
5—Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic55.7$105921 s
6—GPT-5.6 Terra (max)ClosedOpenAI55.0$5.6136140 s
7—GPT-5.5 (xhigh)ClosedOpenAI54.8$117678 s
8—GPT-5.6 Sol (medium)ClosedOpenAI53.6$11524.9 s
9—Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.5$105020 s
10—Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.4$4.083192 s
11—GPT-5.5 (high)ClosedOpenAI53.1$117125 s
12—GPT-5.6 Terra (xhigh)ClosedOpenAI51.6$5.612612 s
13—GPT-5.4 (xhigh)ClosedOpenAI51.4$5.6140112 s
14—GPT-5.6 Luna (max)ClosedOpenAI51.2$2.3192108 s
15—Muse Spark 1.1 (xhigh)ClosedMeta50.6$2.01221.3 s
16—GPT-5.5 (medium)ClosedOpenAI50.4$11724.9 s
17—Gemini 3.5 Flash (high)ClosedGoogle50.2$3.416921 s
18—GPT-5.6 Sol (low)ClosedOpenAI49.4$11523.4 s
19—GPT-5.6 Luna (xhigh)ClosedOpenAI49.1$2.319532 s
20—GPT-5.6 Terra (high)ClosedOpenAI49.0$5.61202.4 s
21—Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic47.2$6.054108 s
22—Gemini 3.1 Pro PreviewClosedGoogle46.5$4.512426 s
23—GPT-5.6 Luna (high)ClosedOpenAI46.1$2.31896.7 s
24—GPT-5.6 Terra (medium)ClosedOpenAI45.6$5.61191.3 s
25—Gemini 3.5 Flash (medium)ClosedGoogle45.4$3.416915 s
26—GPT-5.3 Codex (xhigh)ClosedOpenAI44.3$4.811667 s
27—Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic43.7$104214 s
28—GPT-5.5 (low)ClosedOpenAI43.5$11701.6 s
29—Muse SparkClosedMeta43.1———
30—Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic42.7$10461.6 s
31—GPT-5.2 (xhigh)ClosedOpenAI42.2$4.874114 s
32—Claude Sonnet 5 (Non-reasoning, High Effort)ClosedAnthropic41.7$4.0651.2 s
33—GPT-5.6 Sol (Non-reasoning)ClosedOpenAI41.2$11601.0 s
34—Claude Opus 4.5 (Reasoning)ClosedAnthropic40.8$104713 s
35NewInkling (xhigh)OpenThinking Machines40.7$2.6——
36▼ 1GPT-5.6 Terra (low)ClosedOpenAI40.5$5.61251.2 s
37▼ 1GPT-5.2 Codex (xhigh)ClosedOpenAI40.1$4.817452 s
38▼ 1GPT-5.4 mini (xhigh)ClosedOpenAI40.0$1.71657.8 s
39▼ 1Gemini 3 Pro Preview (high)ClosedGoogle39.6$4.5——
40▼ 1GPT-5.4 (low)ClosedOpenAI39.1$5.6981.4 s
41▼ 1GPT-5.4 nano (xhigh)ClosedOpenAI38.2$0.461714.5 s
42▼ 1GPT-5.6 Luna (medium)ClosedOpenAI38.1$2.31891.7 s
43▼ 1GPT-5.2 (medium)ClosedOpenAI38.0$4.8——
44▼ 1Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic37.8$10392.4 s
45▼ 1Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA37.8$1.22181.2 s
46▼ 1Gemini 3 Flash Preview (Reasoning)ClosedGoogle37.8$1.11776.6 s
47▼ 1GPT-5.1 (high)ClosedOpenAI36.9$3.410031 s
48▼ 1Claude 4.5 Sonnet (Reasoning)ClosedAnthropic36.4$6.04315 s
49▼ 1GPT-5 Codex (high)ClosedOpenAI36.1$3.417311 s
50▼ 1Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic35.9$6.0431.8 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 “—”.