Skip to content
IFAI

Model rankings

1209 models · 5 boards · 2 sources

‹
Week of May 11, 2026
June 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 changesApril 13, 202637 changesApril 6, 202641 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated May 15, 2026

Smartest
GPT-5.5 (xhigh)OpenAI60.2Intelligence
Best open model
Kimi K2.6Kimi53.9Intelligence
Best value
Qwen3.5 0.8B (Reasoning)Alibaba526 pts/$Value
Best from China
Kimi K2.6Kimi53.9Intelligence
Top three by Intelligence
1GPT-5.5 (xhigh)OpenAI60.2
2Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic57.3
3Gemini 3.1 Pro PreviewGoogle57.2
Top three open models
1Kimi K2.6Kimi · #5 overall53.9
2MiMo-V2.5-ProXiaomi · #6 overall53.8
3DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #13 overall51.5
This week's changes
gpt-5.5-xhigh (codex-harness)Coding · #7New
HiDream-O1-Image-Dev-2604Image · #11New
HiDream-O1-ImageImage · #31New
JT-35B-FlashIntelligence · #67New
granite-4.1-8bCoding · #68New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—GPT-5.5 (xhigh)ClosedOpenAI60.2$117081 s
2—GPT-5.5 (high)ClosedOpenAI58.9$116330 s
3—Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic57.3$116615 s
4—Gemini 3.1 Pro PreviewClosedGoogle57.2$4.513533 s
5—GPT-5.4 (xhigh)ClosedOpenAI56.8$5.684222 s
6—GPT-5.5 (medium)ClosedOpenAI56.7$116310 s
7—GPT-5.3 Codex (xhigh)ClosedOpenAI53.6$4.880106 s
8NewGrok 4.3 (high)ClosedxAI53.2$1.6839.0 s
9—Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic52.9$114319 s
10—Muse SparkClosedMeta52.2———
11—Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic51.8$11591.8 s
12—Qwen3.6 Max PreviewClosedAlibaba51.8$2.9374.0 s
13—Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic51.7$6.671115 s
14—GPT-5.2 (xhigh)ClosedOpenAI51.3$4.871216 s
15—GPT-5.5 (low)ClosedOpenAI50.8$11622.5 s
16—Qwen3.6 PlusClosedAlibaba50.0$1.1533.0 s
17—Claude Opus 4.5 (Reasoning)ClosedAnthropic49.7$115014 s
18—Grok 4.20 0309 v2 (Reasoning)ClosedxAI49.3$3.09429 s
19—MiMo-V2-ProClosedXiaomi49.2$1.5732.5 s
20—GPT-5.2 Codex (xhigh)ClosedOpenAI49.0$4.810743 s
21—GPT-5.4 mini (xhigh)ClosedOpenAI48.9$1.716511 s
22—Grok 4.20 0309 (Reasoning)ClosedxAI48.5$3.09230 s
23—Gemini 3 Pro Preview (high)ClosedGoogle48.4$4.514137 s
24—GPT-5.4 (low)ClosedOpenAI47.9$5.6732.4 s
25—GPT-5.1 (high)ClosedOpenAI47.7$3.411545 s
26—GLM-5-TurboClosedZ AI46.8———
27—GPT-5.2 (medium)ClosedOpenAI46.6$4.8——
28—Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic46.5$11422.0 s
29—Gemini 3 Flash Preview (Reasoning)ClosedGoogle46.4$1.11707.4 s
30—MiMo-V2-Omni-0327ClosedXiaomi44.9$0.801072.6 s
31—GPT-5 Codex (high)ClosedOpenAI44.6$3.41829.6 s
32▼ 1GPT-5 (high)ClosedOpenAI44.6$3.48479 s
33—Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic44.4$6.6461.5 s
34—GPT-5.4 nano (xhigh)ClosedOpenAI44.0$0.461455.9 s
35—MiMo-V2-OmniClosedXiaomi43.4$0.0001012.5 s
36—GPT-5.1 Codex (high)ClosedOpenAI43.1$3.41814.4 s
37—Claude Opus 4.5 (Non-reasoning)ClosedAnthropic43.1$11471.7 s
38—Claude 4.5 Sonnet (Reasoning)ClosedAnthropic43.0$6.64413 s
39—GLM 5V Turbo (Reasoning)ClosedZ AI42.9———
40—Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic42.6$6.6481.4 s
41—GPT-5 (medium)ClosedOpenAI42.0$3.49440 s
42—Claude 4.1 Opus (Reasoning)ClosedAnthropic42.0$333514 s
43—Grok 4ClosedxAI41.5$8.54532 s
44—Gemini 3 Pro Preview (low)ClosedGoogle41.3$4.5——
45—GPT-5 mini (high)ClosedOpenAI41.2$0.6992126 s
46—GPT-5.5 (Non-reasoning)ClosedOpenAI40.9$11610.9 s
47—o3-proClosedOpenAI40.7$3529106 s
48—Qwen3 Max ThinkingClosedAlibaba39.8$2.4473.7 s
49—GPT-5 (low)ClosedOpenAI39.2$3.4847.4 s
50—Claude 4 Opus (Reasoning)ClosedAnthropic39.0$333712 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 “—”.