Skip to content
IFAI

Model rankings

1090 models · 5 boards · 2 sources

‹
Week of March 30, 2026
May 11, 202665 changesMay 4, 202616 changesApril 27, 202624 changesApril 20, 202627 changesApril 13, 202637 changesApril 6, 202641 changesMarch 30, 2026230 changesMarch 23, 202626 changesMarch 16, 202622 changesMarch 9, 202665 changesMarch 2, 202663 changesFebruary 23, 202613 changes
›
Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated March 31, 2026

Smartest
Gemini 3.1 Pro PreviewGoogle57.2Intelligence
Best open model
GLM-5 (Reasoning)Z AI49.8Intelligence
Best value
Qwen3.5 0.8B (Reasoning)Alibaba526 pts/$Value
Best from China
GLM-5 (Reasoning)Z AI49.8Intelligence
Top three by Intelligence
1Gemini 3.1 Pro PreviewGoogle57.2
2GPT-5.4 (xhigh)OpenAI57.2
3GPT-5.3 Codex (xhigh)OpenAI54.0
Top three open models
1GLM-5 (Reasoning)Z AI · #7 overall49.8
2Kimi K2.5 (Reasoning)Kimi · #16 overall46.8
3Qwen3.5 397B A17B (Reasoning)Alibaba · #19 overall45.1
This week's changes
qwen3.6-plus-previewCoding · #7New
gpt-5.4-mini-highCoding · #28New
Nemotron Cascade 2 30B A3BIntelligence · #78New
GPT-4Intelligence · #204New
Solar MiniIntelligence · #217New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortIntelligenceValueSpeedLowest price
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—Gemini 3.1 Pro PreviewClosedGoogle57.2$4.510830 s
2—GPT-5.4 (xhigh)ClosedOpenAI57.2$5.673152 s
3—GPT-5.3 Codex (xhigh)ClosedOpenAI54.0$4.87496 s
4—Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic53.0$10418.0 s
5—Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic51.7$6.04578 s
6—GPT-5.2 (xhigh)ClosedOpenAI51.3$4.873122 s
7—GLM-5 (Reasoning)OpenZ AI49.8$1.6721.6 s
8—Claude Opus 4.5 (Reasoning)ClosedAnthropic49.7$104616 s
9—MiniMax-M2.7ClosedMiniMax49.6$0.52453.2 s
10—MiMo-V2-ProClosedXiaomi49.2$1.5——
11—GPT-5.2 Codex (xhigh)ClosedOpenAI49.0$4.811690 s
12—Grok 4.20 Beta 0309 (Reasoning)ClosedxAI48.5$3.02179.8 s
13—Gemini 3 Pro Preview (high)ClosedGoogle48.4$4.510833 s
14—GPT-5.4 mini (xhigh)ClosedOpenAI48.1$1.71903.4 s
15—GPT-5.1 (high)ClosedOpenAI47.7$3.411152 s
16—Kimi K2.5 (Reasoning)OpenKimi46.8$1.2432.8 s
17—GLM-5-TurboClosedZ AI46.8———
18—GPT-5.2 (medium)ClosedOpenAI46.6$4.8——
19—Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic46.5$10381.8 s
20—Gemini 3 Flash Preview (Reasoning)ClosedGoogle46.4$1.11568.0 s
21—Qwen3.5 397B A17B (Reasoning)OpenAlibaba45.1$1.4962.3 s
22—GPT-5 (high)ClosedOpenAI44.6$3.49770 s
22—GPT-5 Codex (high)ClosedOpenAI44.6$3.41704.4 s
24—GPT-5.4 nano (xhigh)ClosedOpenAI44.4$0.461983.3 s
25—Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic44.4$6.0431.5 s
26NewMiMo-V2-OmniClosedXiaomi43.4———
27—GPT-5.1 Codex (high)ClosedOpenAI43.1$3.41554.6 s
28—Claude Opus 4.5 (Non-reasoning)ClosedAnthropic43.1$10451.0 s
29—Claude 4.5 Sonnet (Reasoning)ClosedAnthropic43.0$6.0429.8 s
30—Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic42.6$6.0421.4 s
31—GLM-4.7 (Reasoning)OpenZ AI42.1$1.0791.1 s
32—Qwen3.5 27B (Reasoning)OpenAlibaba42.1$0.83875.6 s
33—GPT-5 (medium)ClosedOpenAI42.0$3.48330 s
34—Claude 4.1 Opus (Reasoning)ClosedAnthropic42.0$302914 s
35—MiniMax-M2.5OpenMiniMax41.9$0.52512.1 s
36—DeepSeek V3.2 (Reasoning)OpenDeepSeek41.7$0.32341.9 s
37—Qwen3.5 122B A10B (Reasoning)OpenAlibaba41.6$1.11402.3 s
38—Grok 4ClosedxAI41.5$6.05216 s
39—MiMo-V2-Flash (Feb 2026)OpenXiaomi41.5$0.151202.4 s
40—Gemini 3 Pro Preview (low)ClosedGoogle41.3$4.5——
41—GPT-5 mini (high)ClosedOpenAI41.2$0.698668 s
42—Kimi K2 ThinkingOpenKimi40.9$1.11051.4 s
43—o3-proClosedOpenAI40.7$352685 s
44—GLM-5 (Non-reasoning)OpenZ AI40.6$1.6591.6 s
45—Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba40.1$1.4912.5 s
46—Qwen3 Max ThinkingClosedAlibaba39.9$2.4373.8 s
47—MiniMax-M2.1OpenMiniMax39.4$0.52502.5 s
48—MiMo-V2-Flash (Reasoning)OpenXiaomi39.2$0.151252.3 s
49—GPT-5 (low)ClosedOpenAI39.2$3.4807.3 s
50—Claude 4 Opus (Reasoning)ClosedAnthropic39.0$30309.8 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 “—”.