Skip to content
IFAI

Model rankings

1356 models · 5 boards · 2 sources

‹
Week of July 6, 2026
August 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 changesJune 8, 202624 changesJune 1, 202622 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated July 11, 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
GLM-5.2 (max)Z AI51.1Intelligence
Top three by Intelligence
1Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic59.9
2GPT-5.6 Sol (max)OpenAI58.9
3Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic55.7
Top three open models
1GLM-5.2 (max)Z AI · #11 overall51.1
2MiniMax-M3MiniMax · #17 overall44.4
3DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #18 overall44.3
This week's changes
gpt-5.6-sol-xhigh (codex-harness)Coding · #1New
Simba 3.2Speech · #1New
GPT-5.6 Sol (max)Intelligence · #2New
GPT-5.6 Terra (max)Intelligence · #4New
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Image · #5New
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$2059113 s
2NewGPT-5.6 Sol (max)ClosedOpenAI58.9$1173154 s
3NewGPT-5.6 Sol (xhigh)ClosedOpenAI57.7$116957 s
4NewGPT-5.6 Sol (high)ClosedOpenAI55.9$116211 s
5▼ 3Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic55.7$105829 s
6NewGPT-5.6 Terra (max)ClosedOpenAI55.0$5.6140154 s
7▼ 4GPT-5.5 (xhigh)ClosedOpenAI54.8$116699 s
8NewGrok 4.5 (high)ClosedSpaceXAI53.8$3.09314 s
9NewGPT-5.6 Sol (medium)ClosedOpenAI53.6$11614.6 s
10▼ 6Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.5$104722 s
11▼ 6Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.4$4.079212 s
12▼ 6GPT-5.5 (high)ClosedOpenAI53.1$116328 s
13NewGPT-5.6 Terra (xhigh)ClosedOpenAI51.6$5.613428 s
14▼ 7GPT-5.4 (xhigh)ClosedOpenAI51.4$5.6149107 s
15NewGPT-5.6 Luna (max)ClosedOpenAI51.2$2.3204100 s
16NewMuse Spark 1.1 (xhigh)ClosedMeta50.6$2.01161.0 s
17▼ 9GPT-5.5 (medium)ClosedOpenAI50.4$11599.7 s
18▼ 9Gemini 3.5 Flash (high)ClosedGoogle50.2$3.415824 s
19NewGPT-5.6 Sol (low)ClosedOpenAI49.4$11632.2 s
20NewGPT-5.6 Luna (xhigh)ClosedOpenAI49.1$2.319334 s
21NewGPT-5.6 Terra (high)ClosedOpenAI49.0$5.61202.5 s
22▼ 12Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic47.2$6.054114 s
23▼ 12Gemini 3.1 Pro PreviewClosedGoogle46.5$4.513625 s
24NewGPT-5.6 Luna (high)ClosedOpenAI46.1$2.31975.8 s
25▼ 13Qwen3.7 MaxClosedAlibaba46.0$3.81942.5 s
26NewGPT-5.6 Terra (medium)ClosedOpenAI45.6$5.61161.5 s
27▼ 14Gemini 3.5 Flash (medium)ClosedGoogle45.4$3.415017 s
28▼ 14GPT-5.3 Codex (xhigh)ClosedOpenAI44.3$4.87779 s
29▼ 14Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic43.7$104116 s
30▼ 14GPT-5.5 (low)ClosedOpenAI43.5$11581.8 s
31▼ 14Muse SparkClosedMeta43.1———
32▼ 14Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic42.7$10431.6 s
33▼ 14GPT-5.2 (xhigh)ClosedOpenAI42.2$4.861108 s
34▼ 14Claude Sonnet 5 (Non-reasoning, High Effort)ClosedAnthropic41.7$4.0741.4 s
35NewGPT-5.6 Sol (Non-reasoning)ClosedOpenAI41.2$11——
36▼ 15Claude Opus 4.5 (Reasoning)ClosedAnthropic40.8$104716 s
37NewGPT-5.6 Terra (low)ClosedOpenAI40.5$5.61201.5 s
38▼ 16MiMo-V2-ProClosedXiaomi40.3$1.5——
39▼ 16GPT-5.2 Codex (xhigh)ClosedOpenAI40.1$4.816071 s
40▼ 16Qwen3.6 Max PreviewClosedAlibaba40.0$2.9473.3 s
41▼ 16GPT-5.4 mini (xhigh)ClosedOpenAI40.0$1.71605.4 s
42▼ 16Grok Build 0.1 0616ClosedSpaceXAI39.8$1.3660.5 s
43▼ 16Qwen3.6 PlusClosedAlibaba39.6$1.1532.8 s
44▼ 16Gemini 3 Pro Preview (high)ClosedGoogle39.6$4.5——
45▼ 16GPT-5.4 (low)ClosedOpenAI39.1$5.6971.5 s
46▼ 16Qwen3.7 PlusClosedAlibaba39.0$0.70513.1 s
47NewJT-4.1 Flash 236B A21BClosedChina Mobile38.8———
48▼ 17GPT-5.4 nano (xhigh)ClosedOpenAI38.2$0.461734.8 s
49▼ 17GLM-5-TurboClosedZ AI38.1———
50NewGPT-5.6 Luna (medium)ClosedOpenAI38.1$2.31931.8 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 “—”.