Skip to content
IFAI

Model rankings

1190 models · 5 boards · 2 sources

‹
Week of April 27, 2026
June 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 changesMarch 30, 2026230 changesMarch 23, 202626 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated May 1, 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-high (codex-harness)Coding · #7New
Grok 4.3Intelligence · #8New
mimo-v2.5-proCoding · #9New
DeepSeek V4 Pro (Reasoning, Max Effort)Intelligence · #13New
gpt-5.5 (codex-harness)Coding · #15New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—GPT-5.5 (xhigh)ClosedOpenAI60.2$1166118 s
2—GPT-5.5 (high)ClosedOpenAI58.9$116341 s
3—Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic57.3$104926 s
4—Gemini 3.1 Pro PreviewClosedGoogle57.2$4.512225 s
5—GPT-5.4 (xhigh)ClosedOpenAI56.8$5.688215 s
6—GPT-5.5 (medium)ClosedOpenAI56.7$11588.2 s
7▲ 1GPT-5.3 Codex (xhigh)ClosedOpenAI53.6$4.87294 s
8NewGrok 4.3ClosedxAI53.2$1.620313 s
9—Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.0$104623 s
10—Muse SparkClosedMeta52.2———
11—Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic51.8$10391.5 s
12—Qwen3.6 Max PreviewClosedAlibaba51.8$2.9333.6 s
13—Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic51.7$6.060117 s
14—GPT-5.2 (xhigh)ClosedOpenAI51.3$4.868159 s
15—GPT-5.5 (low)ClosedOpenAI50.8$11592.4 s
16—Qwen3.6 PlusClosedAlibaba50.0$1.1522.9 s
17—Claude Opus 4.5 (Reasoning)ClosedAnthropic49.7$105016 s
18—Grok 4.20 0309 v2 (Reasoning)ClosedxAI49.3$3.09326 s
19—MiMo-V2-ProClosedXiaomi49.2$1.5623.4 s
20—GPT-5.2 Codex (xhigh)ClosedOpenAI49.0$4.811244 s
21—GPT-5.4 mini (xhigh)ClosedOpenAI48.9$1.71648.8 s
22—Grok 4.20 0309 (Reasoning)ClosedxAI48.5$3.09319 s
23—Gemini 3 Pro Preview (high)ClosedGoogle48.4$4.512828 s
24NewGPT-5.4 (low)ClosedOpenAI47.9$5.6632.2 s
25▼ 1GPT-5.1 (high)ClosedOpenAI47.7$3.412039 s
26▼ 1GLM-5-TurboClosedZ AI46.8———
27▼ 1GPT-5.2 (medium)ClosedOpenAI46.6$4.8——
28▼ 1Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic46.5$10391.7 s
29▼ 1Gemini 3 Flash Preview (Reasoning)ClosedGoogle46.4$1.11657.7 s
30▼ 1MiMo-V2-Omni-0327ClosedXiaomi44.9$0.0001192.2 s
31▼ 1GPT-5 (high)ClosedOpenAI44.6$3.47988 s
31▼ 1GPT-5 Codex (high)ClosedOpenAI44.6$3.41767.4 s
33▼ 1Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic44.4$6.0451.2 s
34▼ 1GPT-5.4 nano (xhigh)ClosedOpenAI44.0$0.461605.0 s
35▼ 1MiMo-V2-OmniClosedXiaomi43.4$0.0001182.0 s
36▼ 1GPT-5.1 Codex (high)ClosedOpenAI43.1$3.41768.1 s
37▼ 1Claude Opus 4.5 (Non-reasoning)ClosedAnthropic43.1$10471.5 s
38▼ 1Claude 4.5 Sonnet (Reasoning)ClosedAnthropic43.0$6.04510 s
39▼ 1GLM 5V Turbo (Reasoning)ClosedZ AI42.9———
40▼ 1Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic42.6$6.0491.3 s
41▼ 1GPT-5 (medium)ClosedOpenAI42.0$3.47546 s
42▼ 1Claude 4.1 Opus (Reasoning)ClosedAnthropic42.0$303313 s
43▼ 1Grok 4ClosedxAI41.5$6.04912 s
44▼ 1Gemini 3 Pro Preview (low)ClosedGoogle41.3$4.5——
45▼ 1GPT-5 mini (high)ClosedOpenAI41.2$0.6972118 s
46▼ 1GPT-5.5 (Non-reasoning)ClosedOpenAI40.9$11561.2 s
47▼ 1o3-proClosedOpenAI40.7$3527105 s
48▼ 1Qwen3 Max ThinkingClosedAlibaba39.9$2.4403.7 s
49▼ 1GPT-5 (low)ClosedOpenAI39.2$3.48112 s
50▼ 1Claude 4 Opus (Reasoning)ClosedAnthropic39.0$303311 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 “—”.