AI Performance Rankings — Coding, Math, Image & Speed | aib vote

Overall

Source: Artificial Analysis

AA Intelligence Index

A composite intelligence score by Artificial Analysis. Aggregates reasoning, coding, math, and language understanding benchmarks into a single weighted metric.

🥇 No.1

Anthropic

Claude Opus 4.7

57.3↑18.6

🥈 No.2

Google

57.2↑18.5

🥉 No.3

OpenAI

56.8↑18.1

No.4

Anthropic

Claude Opus 4.6

53.0↑14.3

No.5

Meta

52.1↑13.4

No.6

DeepSeek

DeepSeek V4 Pro

51.5↑12.8

No.7

Z.ai

51.4↑12.7

No.8

Alibaba

50.0↑11.3

No.9

Z.ai

49.8↑11.1

No.10

Anthropic

Claude Opus 4.5

49.7↑11.0

No.11

MiniMax

49.6↑10.9

No.12

Grok

Grok 4.20 (Reasoning)

49.3↑10.6

No.13

Xiaomi

49.2↑10.5

No.14

Moonshot AI

46.8↑8.1

No.15

DeepSeek

DeepSeek V4 Flash

46.5↑7.8

No.16

Google

46.4↑7.7

No.17

Anthropic

Claude Sonnet 4.5

43.0↑4.3

No.18

Anthropic

Claude Sonnet 4.6

42.6↑3.9

No.19

Anthropic

Claude Opus 4.1

42.0↑3.3

No.20

MiniMax

41.9↑3.2

No.21

DeepSeek

41.7↑3.0

No.22

Alibaba

Qwen3.5 397B A17B

40.1↑1.4

No.23

Google

39.2↑0.5

No.24

Anthropic

39.0↑0.3

No.25

Anthropic

Claude Sonnet 4

38.7↑0.0

No.26

Grok

Grok 4.1 Fast (Reasoning)

38.6↓0.1

No.27

OpenAI

38.1↓0.6

No.28

OpenAI

37.7↓1.0

No.29

Anthropic

Claude Haiku 4.5

37.1↓1.6

No.30

NVIDIA

Nemotron 3 Super

36.0↓2.7

No.31

Google

34.6↓4.1

No.32

Google

Gemini 3.1 Flash Lite

33.5↓5.2

No.33

LG AI Research

32.0↓6.7

No.34

Arcee AI

Trinity Large Thinking

31.9↓6.8

No.35

Baidu

ERNIE 5.0 Thinking

29.1↓9.6

No.36

Grok

29.0↓9.7

No.37

Mistral AI

Mistral Small 4

27.8↓10.9

No.38

Google

Gemini 2.5 Flash

27.0↓11.7

No.39

OpenAI

26.3↓12.4

No.40

OpenAI

25.9↓12.8

No.41

OpenAI

24.5↓14.2

No.42

Meituan

Longcat Flash Chat

23.9↓14.8

No.43

Grok

23.6↓15.1

No.44

OpenAI

21.8↓16.9

No.45

OpenAI

20.7↓18.0

No.46

Google

Gemini 2.5 Flash Lite

19.4↓19.3

No.47

Meta

Llama 4 Maverick

18.4↓20.3

No.48

Amazon

18.0↓20.7

No.49

Baidu

ERNIE 4.5 300B A47B

15.0↓23.7

No.50

Meta

13.5↓25.2