Artificial Analysis Agentic Index leaderboard & scores

Accessible data for Artificial Analysis Agentic Index leaderboard
Model	Rank	Provider	Score
GPT-5.6 Sol	#1	OpenAI	54 index
Claude Fable 5	#2	Anthropic	52.8 index
Kimi K3	#3	Moonshot AI	50.1 index
GPT-5.6 Terra	#4	OpenAI	47.4 index
Claude Opus 4.8	#5	Anthropic	47.2 index
Claude Sonnet 5	#6	Anthropic	46.7 index
Grok 4.5	#7	xAI	45.7 index
GPT-5.6 Luna	#8	OpenAI	45.6 index
GPT-5.5	#9	OpenAI	44.9 index
Claude Opus 4.7 (Adaptive)	#10	Anthropic	44.4 index
GLM-5.2	#11	Z.AI	43.1 index
GPT-5.4	#12	OpenAI	41.1 index
Gemini 3.6 Flash	#13	Google	38.7 index
Muse Spark 1.1	#14	Meta	37.5 index
Gemini 3.5 Flash	#15	Google	37.5 index
DeepSeek V4 Pro (Max)	#16	DeepSeek	36.4 index
MiniMax M3	#17	MiniMax	35.4 index
DeepSeek V4 Pro (High)	#18	DeepSeek	34.4 index
Inkling	#19	Thinking Machines Lab	32.3 index
DeepSeek V4 Flash (Max)	#20	DeepSeek	31.1 index

Model

Rank

Provider

Score

GPT-5.6 Sol

OpenAI

54 index

Claude Fable 5

Anthropic

52.8 index

Kimi K3

Moonshot AI

50.1 index

GPT-5.6 Terra

OpenAI

47.4 index

Claude Opus 4.8

Anthropic

47.2 index

Claude Sonnet 5

Anthropic

46.7 index

Grok 4.5

xAI

45.7 index

GPT-5.6 Luna

OpenAI

45.6 index

GPT-5.5

OpenAI

44.9 index

Claude Opus 4.7 (Adaptive)

#10

Anthropic

44.4 index

GLM-5.2

#11

Z.AI

43.1 index

GPT-5.4

#12

OpenAI

41.1 index

Gemini 3.6 Flash

#13

Google

38.7 index

Muse Spark 1.1

#14

Meta

37.5 index

Gemini 3.5 Flash

#15

Google

37.5 index

DeepSeek V4 Pro (Max)

#16

DeepSeek

36.4 index

MiniMax M3

#17

MiniMax

35.4 index

DeepSeek V4 Pro (High)

#18

DeepSeek

34.4 index

Inkling

#19

Thinking Machines Lab

32.3 index

DeepSeek V4 Flash (Max)

#20

DeepSeek

31.1 index

Artificial Analysis Agentic Index leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	GPT-5.6 Sol gpt-5.6-sol	OpenAI	closed	Reference only	54 index
#2	Claude Fable 5 claude-fable-5	Anthropic	closed	Reference only	52.8 index
#3	Kimi K3 kimi-k3	Moonshot AI	closed	Reference only	50.1 index
#4	GPT-5.6 Terra gpt-5.6-terra	OpenAI	closed	Estimated reference	47.4 index
#5	Claude Opus 4.8 claude-opus-4-8	Anthropic	closed	Reference only	47.2 index
#6	Claude Sonnet 5 claude-sonnet-5	Anthropic	closed	Estimated reference	46.7 index
#7	Grok 4.5 grok-4.5	xAI	closed	Reference only	45.7 index
#8	GPT-5.6 Luna gpt-5.6-luna	OpenAI	closed	Estimated reference	45.6 index
#9	GPT-5.5 gpt-5.5	OpenAI	closed	Estimated reference	44.9 index
#10	Claude Opus 4.7 (Adaptive) claude-opus-4-7-max	Anthropic	closed	Estimated reference	44.4 index
#11	GLM-5.2 glm-5-2	Z.AI	open	Estimated reference	43.1 index
#12	GPT-5.4 gpt-5.4	OpenAI	closed	Reference only	41.1 index
#13	Gemini 3.6 Flash gemini-3.6-flash	Google	closed	Estimated reference	38.7 index
#14	Muse Spark 1.1 muse-spark-1-1	Meta	closed	Reference only	37.5 index
#15	Gemini 3.5 Flash gemini-3.5-flash	Google	closed	Estimated reference	37.5 index
#16	DeepSeek V4 Pro (Max) deepseek-v4-pro-max	DeepSeek	open	Estimated reference	36.4 index
#17	MiniMax M3 MiniMax-M3	MiniMax	—	Reference only	35.4 index
#18	DeepSeek V4 Pro (High) deepseek-v4-pro-high	DeepSeek	open	Estimated reference	34.4 index
#19	Inkling inkling	Thinking Machines Lab	open	Reference only	32.3 index
#20	DeepSeek V4 Flash (Max) deepseek-v4-flash-max	DeepSeek	open	Estimated reference	31.1 index
#21	Hy3 hy3	Tencent	open	Estimated reference	30.7 index
#22	Hy3 Preview hy3-preview	Tencent	open	Estimated reference	30.7 index
#23	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	30.6 index
#24	Kimi K2.6 kimi-k2.6	Moonshot AI	open	Estimated reference	30.3 index
#25	GPT-5.4 mini gpt-5.4-mini	OpenAI	closed	Estimated reference	30.2 index
#26	GLM-5.1 glm-5-1	Z.AI	open	Reference only	29.9 index
#27	Kimi K2.7 Code kimi-k2.7-code	Moonshot AI	open	Estimated reference	29.6 index
#28	MiMo-V2.5-Pro mimo-v2-5-pro	Xiaomi	closed	Reference only	29.1 index
#29	Muse Spark muse-spark	Meta	closed	Reference only	28.7 index
#30	DeepSeek V4 Flash (High) deepseek-v4-flash-high	DeepSeek	open	Estimated reference	28.2 index
#31	Qwen3.6 Plus qwen3-6-plus	Alibaba Cloud	closed	Reference only	27.6 index
#32	GPT-5.4 nano gpt.5.4.nano	OpenAI	closed	Reference only	27.5 index
#33	Nemotron 3 Ultra nemotron-3-ultra-550b	NVIDIA	open	Estimated reference	27.4 index
#34	Qwen3.6 27B qwen3.6-27b	Alibaba Cloud	open	Estimated reference	27.0 index
#35	Gemini 3.5 Flash-Lite gemini-3.5-flash-lite	Google	closed	Estimated reference	26.8 index
#36	GPT-5 (high) gpt-5-high	OpenAI	closed	Estimated reference	25.7 index
#37	MiniMax M2.7 minimax-m2-7	MiniMax	open	Reference only	25.6 index
#38	GLM-4.7 glm-4.7	Z.AI	open	Reference only	25.4 index
#39	Grok 4.3 grok-4.3	xAI	closed	Reference only	24.1 index
#40	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	21.7 index
#41	Kimi K2.5 (Reasoning) kimi-k2-5-reasoning	Moonshot AI	closed	Estimated reference	21.7 index
#42	Step 3.7 Flash step-3-7-flash	StepFun	open	Estimated reference	21.5 index
#43	Qwen3.6-35B-A3B qwen3-6-35b-a3b	Alibaba Cloud	open	Estimated reference	21.4 index
#44	Gemini 3.1 Pro gemini-3-1-pro	Google	closed	Estimated reference	21.4 index
#45	GPT-5.1 gpt.5.1	OpenAI	closed	Estimated reference	21.0 index
#46	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	20.8 index
#47	Qwen3.5-122B-A10B qwen3-5-122b-a10b	Alibaba Cloud	open	Reference only	20.7 index
#48	Qwen3.5 397B qwen3.5-397b-a17b	Alibaba Cloud	open	Estimated reference	19.9 index
#49	Qwen3.5 397B (Reasoning) qwen3-5-397b-reasoning	Alibaba Cloud	open	Estimated reference	19.9 index
#50	Mistral Medium 3.5 128B mistral-medium-3-5-128b	Mistral AI	open	Estimated reference	19 index
#51	Gemma 4 31B gemma-4-31b	Google	open	Reference only	14.4 index
#52	GPT-OSS 120B gpt-oss-120b	OpenAI	open	Reference only	13.2 index
#53	MiMo-V2-Flash mimo-v2-flash	Xiaomi	open	Reference only	12.0 index
#54	Gemma 4 26B A4B gemma-4-26b-a4b	Google	open	Reference only	11.0 index
#55	Command A+ command-a-plus	Cohere	open	Estimated reference	9.2 index
#56	Gemini 2.5 Pro gemini-2.5-pro	Google	closed	Reference only	7.1 index
#57	Gemini 3.1 Flash-Lite gemini-3.1-flash-lite	Google	closed	Reference only	6.2 index
#58	Mistral Large 3 mistral-large-2512	Mistral AI	open	Reference only	5.5 index
#59	Mistral Small 4 mistral-small-2603	Mistral AI	open	Estimated reference	4.7 index
#60	Mistral Small 4 (Reasoning) mistral-small-4-reasoning	Mistral AI	open	Estimated reference	4.7 index
#61	GPT-OSS 20B gpt-oss-20b	OpenAI	open	Reference only	3.1 index
#62	Ling 2.6 Flash ling-2-6-flash	InclusionAI	open	Estimated reference	2.3 index
#63	Nemotron 3 Nano 30B nemotron-3-nano-30b	NVIDIA	open	Estimated reference	2.0 index
#64	GPT-4.1 mini gpt-4-1-mini	OpenAI	closed	Estimated reference	1.7 index
#65	DeepSeek V3 deepseek-v3	DeepSeek	open	Reference only	1.6 index
#66	Llama 4 Maverick llama-4-maverick	Meta	open	Reference only	1.3 index
#67	GPT-4.1 nano gpt-4-1-nano	OpenAI	closed	Estimated reference	1.2 index
#68	Llama 4 Scout llama-4-scout	Meta	open	Reference only	1.1 index
#69	GPT-4o mini gpt-4o-mini	OpenAI	closed	Reference only	1.0 index
#70	Gemma 3 27B gemma-3-27b	Google	open	Reference only	0.3 index

Rank

Model

Provider

License

Evidence use

Score

GPT-5.6 Sol

gpt-5.6-sol

OpenAI

closed

Reference only

54 index

Claude Fable 5

claude-fable-5

Anthropic

closed

Reference only

52.8 index

Kimi K3

kimi-k3

Moonshot AI

closed

Reference only

50.1 index

GPT-5.6 Terra

gpt-5.6-terra

OpenAI

closed

Estimated reference

47.4 index

Claude Opus 4.8

claude-opus-4-8

Anthropic

closed

Reference only

47.2 index

Claude Sonnet 5

claude-sonnet-5

Anthropic

closed

Estimated reference

46.7 index

Grok 4.5

grok-4.5

xAI

closed

Reference only

45.7 index

GPT-5.6 Luna

gpt-5.6-luna

OpenAI

closed

Estimated reference

45.6 index

GPT-5.5

gpt-5.5

OpenAI

closed

Estimated reference

44.9 index

#10

Claude Opus 4.7 (Adaptive)

claude-opus-4-7-max

Anthropic

closed

Estimated reference

44.4 index

#11

GLM-5.2

glm-5-2

Z.AI

open

Estimated reference

43.1 index

#12

GPT-5.4

gpt-5.4

OpenAI

closed

Reference only

41.1 index

#13

Gemini 3.6 Flash

gemini-3.6-flash

Google

closed

Estimated reference

38.7 index

#14

Muse Spark 1.1

muse-spark-1-1

Meta

closed

Reference only

37.5 index

#15

Gemini 3.5 Flash

gemini-3.5-flash

Google

closed

Estimated reference

37.5 index

#16

DeepSeek V4 Pro (Max)

deepseek-v4-pro-max

DeepSeek

open

Estimated reference

36.4 index

#17

MiniMax M3

MiniMax-M3

MiniMax

—

Reference only

35.4 index

#18

DeepSeek V4 Pro (High)

deepseek-v4-pro-high

DeepSeek

open

Estimated reference

34.4 index

#19

Inkling

inkling

Thinking Machines Lab

open

Reference only

32.3 index

#20

DeepSeek V4 Flash (Max)

deepseek-v4-flash-max

DeepSeek

open

Estimated reference

31.1 index

#21

Hy3

hy3

Tencent

open

Estimated reference

30.7 index

#22

Hy3 Preview

hy3-preview

Tencent

open

Estimated reference

30.7 index

#23

Qwen3.7-Max

qwen3.7-max

Alibaba Cloud

—

Reference only

30.6 index

#24

Kimi K2.6

kimi-k2.6

Moonshot AI

open

Estimated reference

30.3 index

#25

GPT-5.4 mini

gpt-5.4-mini

OpenAI

closed

Estimated reference

30.2 index

#26

GLM-5.1

glm-5-1

Z.AI

open

Reference only

29.9 index

#27

Kimi K2.7 Code

kimi-k2.7-code

Moonshot AI

open

Estimated reference

29.6 index

#28

MiMo-V2.5-Pro

mimo-v2-5-pro

Xiaomi

closed

Reference only

29.1 index

#29

Muse Spark

muse-spark

Meta

closed

Reference only

28.7 index

#30

DeepSeek V4 Flash (High)

deepseek-v4-flash-high

DeepSeek

open

Estimated reference

28.2 index

#31

Qwen3.6 Plus

qwen3-6-plus

Alibaba Cloud

closed

Reference only

27.6 index

#32

GPT-5.4 nano

gpt.5.4.nano

OpenAI

closed

Reference only

27.5 index

#33

Nemotron 3 Ultra

nemotron-3-ultra-550b

NVIDIA

open

Estimated reference

27.4 index

#34

Qwen3.6 27B

qwen3.6-27b

Alibaba Cloud

open

Estimated reference

27.0 index

#35

Gemini 3.5 Flash-Lite

gemini-3.5-flash-lite

Google

closed

Estimated reference

26.8 index

#36

GPT-5 (high)

gpt-5-high

OpenAI

closed

Estimated reference

25.7 index

#37

MiniMax M2.7

minimax-m2-7

MiniMax

open

Reference only

25.6 index

#38

GLM-4.7

glm-4.7

Z.AI

open

Reference only

25.4 index

#39

Grok 4.3

grok-4.3

xAI

closed

Reference only

24.1 index

#40

Kimi K2.5

kimi-k2.5

Moonshot AI

—

Reference only

21.7 index

#41

Kimi K2.5 (Reasoning)

kimi-k2-5-reasoning

Moonshot AI

closed

Estimated reference

21.7 index

#42

Step 3.7 Flash

step-3-7-flash

StepFun

open

Estimated reference

21.5 index

#43

Qwen3.6-35B-A3B

qwen3-6-35b-a3b

Alibaba Cloud

open

Estimated reference

21.4 index

#44

Gemini 3.1 Pro

gemini-3-1-pro

Google

closed

Estimated reference

21.4 index

#45

GPT-5.1

gpt.5.1

OpenAI

closed

Estimated reference

21.0 index

#46

Qwen3.7-Plus

qwen3.7-plus

Alibaba Cloud

—

Reference only

20.8 index

#47

Qwen3.5-122B-A10B

qwen3-5-122b-a10b

Alibaba Cloud

open

Reference only

20.7 index

#48

Qwen3.5 397B

qwen3.5-397b-a17b

Alibaba Cloud

open

Estimated reference

19.9 index

#49

Qwen3.5 397B (Reasoning)

qwen3-5-397b-reasoning

Alibaba Cloud

open

Estimated reference

19.9 index

#50

Mistral Medium 3.5 128B

mistral-medium-3-5-128b

Mistral AI

open

Estimated reference

19 index

#51

Gemma 4 31B

gemma-4-31b

Google

open

Reference only

14.4 index

#52

GPT-OSS 120B

gpt-oss-120b

OpenAI

open

Reference only

13.2 index

#53

MiMo-V2-Flash

mimo-v2-flash

Xiaomi

open

Reference only

12.0 index

#54

Gemma 4 26B A4B

gemma-4-26b-a4b

Google

open

Reference only

11.0 index

#55

Command A+

command-a-plus

Cohere

open

Estimated reference

9.2 index

#56

Gemini 2.5 Pro

gemini-2.5-pro

Google

closed

Reference only

7.1 index

#57

Gemini 3.1 Flash-Lite

gemini-3.1-flash-lite

Google

closed

Reference only

6.2 index

#58

Mistral Large 3

mistral-large-2512

Mistral AI

open

Reference only

5.5 index

#59

Mistral Small 4

mistral-small-2603

Mistral AI

open

Estimated reference

4.7 index

#60

Mistral Small 4 (Reasoning)

mistral-small-4-reasoning

Mistral AI

open

Estimated reference

4.7 index

#61

GPT-OSS 20B

gpt-oss-20b

OpenAI

open

Reference only

3.1 index

#62

Ling 2.6 Flash

ling-2-6-flash

InclusionAI

open

Estimated reference

2.3 index

#63

Nemotron 3 Nano 30B

nemotron-3-nano-30b

NVIDIA

open

Estimated reference

2.0 index

#64

GPT-4.1 mini

gpt-4-1-mini

OpenAI

closed

Estimated reference

1.7 index

#65

DeepSeek V3

deepseek-v3

DeepSeek

open

Reference only

1.6 index

#66

Llama 4 Maverick

llama-4-maverick

Meta

open

Reference only

1.3 index

#67

GPT-4.1 nano

gpt-4-1-nano

OpenAI

closed

Estimated reference

1.2 index

#68

Llama 4 Scout

llama-4-scout

Meta

open

Reference only

1.1 index

#69

GPT-4o mini

gpt-4o-mini

OpenAI

closed

Reference only

1.0 index

#70

Gemma 3 27B

gemma-3-27b

Google

open

Reference only

0.3 index

Definition and scoring

Organisation

Artificial Analysis

What does Artificial Analysis Agentic Index measure?

A display-only Artificial Analysis agentic index.

Which model scores highest on Artificial Analysis Agentic Index?

GPT-5.6 Sol by OpenAI currently leads with 54 index.

How many models are evaluated on Artificial Analysis Agentic Index?

70 models in the LuminaBench cohort have a qualifying score on this benchmark.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

Accessible data for Artificial Analysis Agentic Index leaderboard
Model	Rank	Provider	Score
GPT-5.6 Sol	#1	OpenAI	54 index
Claude Fable 5	#2	Anthropic	52.8 index
Kimi K3	#3	Moonshot AI	50.1 index
GPT-5.6 Terra	#4	OpenAI	47.4 index
Claude Opus 4.8	#5	Anthropic	47.2 index
Claude Sonnet 5	#6	Anthropic	46.7 index
Grok 4.5	#7	xAI	45.7 index
GPT-5.6 Luna	#8	OpenAI	45.6 index
GPT-5.5	#9	OpenAI	44.9 index
Claude Opus 4.7 (Adaptive)	#10	Anthropic	44.4 index
GLM-5.2	#11	Z.AI	43.1 index
GPT-5.4	#12	OpenAI	41.1 index
Gemini 3.6 Flash	#13	Google	38.7 index
Muse Spark 1.1	#14	Meta	37.5 index
Gemini 3.5 Flash	#15	Google	37.5 index
DeepSeek V4 Pro (Max)	#16	DeepSeek	36.4 index
MiniMax M3	#17	MiniMax	35.4 index
DeepSeek V4 Pro (High)	#18	DeepSeek	34.4 index
Inkling	#19	Thinking Machines Lab	32.3 index
DeepSeek V4 Flash (Max)	#20	DeepSeek	31.1 index

Model

Rank

Provider

Score

GPT-5.6 Sol

OpenAI

54 index

Claude Fable 5

Anthropic

52.8 index

Kimi K3

Moonshot AI

50.1 index

GPT-5.6 Terra

OpenAI

47.4 index

Claude Opus 4.8

Anthropic

47.2 index

Claude Sonnet 5

Anthropic

46.7 index

Grok 4.5

xAI

45.7 index

GPT-5.6 Luna

OpenAI

45.6 index

GPT-5.5

OpenAI

44.9 index

Claude Opus 4.7 (Adaptive)

#10

Anthropic

44.4 index

GLM-5.2

#11

Z.AI

43.1 index

GPT-5.4

#12

OpenAI

41.1 index

Gemini 3.6 Flash

#13

Google

38.7 index

Muse Spark 1.1

#14

Meta

37.5 index

Gemini 3.5 Flash

#15

Google

37.5 index

DeepSeek V4 Pro (Max)

#16

DeepSeek

36.4 index

MiniMax M3

#17

MiniMax

35.4 index

DeepSeek V4 Pro (High)

#18

DeepSeek

34.4 index

Inkling

#19

Thinking Machines Lab

32.3 index

DeepSeek V4 Flash (Max)

#20

DeepSeek

31.1 index

Artificial Analysis Agentic Index leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	GPT-5.6 Sol gpt-5.6-sol	OpenAI	closed	Reference only	54 index
#2	Claude Fable 5 claude-fable-5	Anthropic	closed	Reference only	52.8 index
#3	Kimi K3 kimi-k3	Moonshot AI	closed	Reference only	50.1 index
#4	GPT-5.6 Terra gpt-5.6-terra	OpenAI	closed	Estimated reference	47.4 index
#5	Claude Opus 4.8 claude-opus-4-8	Anthropic	closed	Reference only	47.2 index
#6	Claude Sonnet 5 claude-sonnet-5	Anthropic	closed	Estimated reference	46.7 index
#7	Grok 4.5 grok-4.5	xAI	closed	Reference only	45.7 index
#8	GPT-5.6 Luna gpt-5.6-luna	OpenAI	closed	Estimated reference	45.6 index
#9	GPT-5.5 gpt-5.5	OpenAI	closed	Estimated reference	44.9 index
#10	Claude Opus 4.7 (Adaptive) claude-opus-4-7-max	Anthropic	closed	Estimated reference	44.4 index
#11	GLM-5.2 glm-5-2	Z.AI	open	Estimated reference	43.1 index
#12	GPT-5.4 gpt-5.4	OpenAI	closed	Reference only	41.1 index
#13	Gemini 3.6 Flash gemini-3.6-flash	Google	closed	Estimated reference	38.7 index
#14	Muse Spark 1.1 muse-spark-1-1	Meta	closed	Reference only	37.5 index
#15	Gemini 3.5 Flash gemini-3.5-flash	Google	closed	Estimated reference	37.5 index
#16	DeepSeek V4 Pro (Max) deepseek-v4-pro-max	DeepSeek	open	Estimated reference	36.4 index
#17	MiniMax M3 MiniMax-M3	MiniMax	—	Reference only	35.4 index
#18	DeepSeek V4 Pro (High) deepseek-v4-pro-high	DeepSeek	open	Estimated reference	34.4 index
#19	Inkling inkling	Thinking Machines Lab	open	Reference only	32.3 index
#20	DeepSeek V4 Flash (Max) deepseek-v4-flash-max	DeepSeek	open	Estimated reference	31.1 index
#21	Hy3 hy3	Tencent	open	Estimated reference	30.7 index
#22	Hy3 Preview hy3-preview	Tencent	open	Estimated reference	30.7 index
#23	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	30.6 index
#24	Kimi K2.6 kimi-k2.6	Moonshot AI	open	Estimated reference	30.3 index
#25	GPT-5.4 mini gpt-5.4-mini	OpenAI	closed	Estimated reference	30.2 index
#26	GLM-5.1 glm-5-1	Z.AI	open	Reference only	29.9 index
#27	Kimi K2.7 Code kimi-k2.7-code	Moonshot AI	open	Estimated reference	29.6 index
#28	MiMo-V2.5-Pro mimo-v2-5-pro	Xiaomi	closed	Reference only	29.1 index
#29	Muse Spark muse-spark	Meta	closed	Reference only	28.7 index
#30	DeepSeek V4 Flash (High) deepseek-v4-flash-high	DeepSeek	open	Estimated reference	28.2 index
#31	Qwen3.6 Plus qwen3-6-plus	Alibaba Cloud	closed	Reference only	27.6 index
#32	GPT-5.4 nano gpt.5.4.nano	OpenAI	closed	Reference only	27.5 index
#33	Nemotron 3 Ultra nemotron-3-ultra-550b	NVIDIA	open	Estimated reference	27.4 index
#34	Qwen3.6 27B qwen3.6-27b	Alibaba Cloud	open	Estimated reference	27.0 index
#35	Gemini 3.5 Flash-Lite gemini-3.5-flash-lite	Google	closed	Estimated reference	26.8 index
#36	GPT-5 (high) gpt-5-high	OpenAI	closed	Estimated reference	25.7 index
#37	MiniMax M2.7 minimax-m2-7	MiniMax	open	Reference only	25.6 index
#38	GLM-4.7 glm-4.7	Z.AI	open	Reference only	25.4 index
#39	Grok 4.3 grok-4.3	xAI	closed	Reference only	24.1 index
#40	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	21.7 index
#41	Kimi K2.5 (Reasoning) kimi-k2-5-reasoning	Moonshot AI	closed	Estimated reference	21.7 index
#42	Step 3.7 Flash step-3-7-flash	StepFun	open	Estimated reference	21.5 index
#43	Qwen3.6-35B-A3B qwen3-6-35b-a3b	Alibaba Cloud	open	Estimated reference	21.4 index
#44	Gemini 3.1 Pro gemini-3-1-pro	Google	closed	Estimated reference	21.4 index
#45	GPT-5.1 gpt.5.1	OpenAI	closed	Estimated reference	21.0 index
#46	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	20.8 index
#47	Qwen3.5-122B-A10B qwen3-5-122b-a10b	Alibaba Cloud	open	Reference only	20.7 index
#48	Qwen3.5 397B qwen3.5-397b-a17b	Alibaba Cloud	open	Estimated reference	19.9 index
#49	Qwen3.5 397B (Reasoning) qwen3-5-397b-reasoning	Alibaba Cloud	open	Estimated reference	19.9 index
#50	Mistral Medium 3.5 128B mistral-medium-3-5-128b	Mistral AI	open	Estimated reference	19 index
#51	Gemma 4 31B gemma-4-31b	Google	open	Reference only	14.4 index
#52	GPT-OSS 120B gpt-oss-120b	OpenAI	open	Reference only	13.2 index
#53	MiMo-V2-Flash mimo-v2-flash	Xiaomi	open	Reference only	12.0 index
#54	Gemma 4 26B A4B gemma-4-26b-a4b	Google	open	Reference only	11.0 index
#55	Command A+ command-a-plus	Cohere	open	Estimated reference	9.2 index
#56	Gemini 2.5 Pro gemini-2.5-pro	Google	closed	Reference only	7.1 index
#57	Gemini 3.1 Flash-Lite gemini-3.1-flash-lite	Google	closed	Reference only	6.2 index
#58	Mistral Large 3 mistral-large-2512	Mistral AI	open	Reference only	5.5 index
#59	Mistral Small 4 mistral-small-2603	Mistral AI	open	Estimated reference	4.7 index
#60	Mistral Small 4 (Reasoning) mistral-small-4-reasoning	Mistral AI	open	Estimated reference	4.7 index
#61	GPT-OSS 20B gpt-oss-20b	OpenAI	open	Reference only	3.1 index
#62	Ling 2.6 Flash ling-2-6-flash	InclusionAI	open	Estimated reference	2.3 index
#63	Nemotron 3 Nano 30B nemotron-3-nano-30b	NVIDIA	open	Estimated reference	2.0 index
#64	GPT-4.1 mini gpt-4-1-mini	OpenAI	closed	Estimated reference	1.7 index
#65	DeepSeek V3 deepseek-v3	DeepSeek	open	Reference only	1.6 index
#66	Llama 4 Maverick llama-4-maverick	Meta	open	Reference only	1.3 index
#67	GPT-4.1 nano gpt-4-1-nano	OpenAI	closed	Estimated reference	1.2 index
#68	Llama 4 Scout llama-4-scout	Meta	open	Reference only	1.1 index
#69	GPT-4o mini gpt-4o-mini	OpenAI	closed	Reference only	1.0 index
#70	Gemma 3 27B gemma-3-27b	Google	open	Reference only	0.3 index

Rank

Model

Provider

License

Evidence use

Score

GPT-5.6 Sol

gpt-5.6-sol

OpenAI

closed

Reference only

54 index

Claude Fable 5

claude-fable-5

Anthropic

closed

Reference only

52.8 index

Kimi K3

kimi-k3

Moonshot AI

closed

Reference only

50.1 index

GPT-5.6 Terra

gpt-5.6-terra

OpenAI

closed

Estimated reference

47.4 index

Claude Opus 4.8

claude-opus-4-8

Anthropic

closed

Reference only

47.2 index

Claude Sonnet 5

claude-sonnet-5

Anthropic

closed

Estimated reference

46.7 index

Grok 4.5

grok-4.5

xAI

closed

Reference only

45.7 index

GPT-5.6 Luna

gpt-5.6-luna

OpenAI

closed

Estimated reference

45.6 index

GPT-5.5

gpt-5.5

OpenAI

closed

Estimated reference

44.9 index

#10

Claude Opus 4.7 (Adaptive)

claude-opus-4-7-max

Anthropic

closed

Estimated reference

44.4 index

#11

GLM-5.2

glm-5-2

Z.AI

open

Estimated reference

43.1 index

#12

GPT-5.4

gpt-5.4

OpenAI

closed

Reference only

41.1 index

#13

Gemini 3.6 Flash

gemini-3.6-flash

Google

closed

Estimated reference

38.7 index

#14

Muse Spark 1.1

muse-spark-1-1

Meta

closed

Reference only

37.5 index

#15

Gemini 3.5 Flash

gemini-3.5-flash

Google

closed

Estimated reference

37.5 index

#16

DeepSeek V4 Pro (Max)

deepseek-v4-pro-max

DeepSeek

open

Estimated reference

36.4 index

#17

MiniMax M3

MiniMax-M3

MiniMax

—

Reference only

35.4 index

#18

DeepSeek V4 Pro (High)

deepseek-v4-pro-high

DeepSeek

open

Estimated reference

34.4 index

#19

Inkling

inkling

Thinking Machines Lab

open

Reference only

32.3 index

#20

DeepSeek V4 Flash (Max)

deepseek-v4-flash-max

DeepSeek

open

Estimated reference

31.1 index

#21

Hy3

hy3

Tencent

open

Estimated reference

30.7 index

#22

Hy3 Preview

hy3-preview

Tencent

open

Estimated reference

30.7 index

#23

Qwen3.7-Max

qwen3.7-max

Alibaba Cloud

—

Reference only

30.6 index

#24

Kimi K2.6

kimi-k2.6

Moonshot AI

open

Estimated reference

30.3 index

#25

GPT-5.4 mini

gpt-5.4-mini

OpenAI

closed

Estimated reference

30.2 index

#26

GLM-5.1

glm-5-1

Z.AI

open

Reference only

29.9 index

#27

Kimi K2.7 Code

kimi-k2.7-code

Moonshot AI

open

Estimated reference

29.6 index

#28

MiMo-V2.5-Pro

mimo-v2-5-pro

Xiaomi

closed

Reference only

29.1 index

#29

Muse Spark

muse-spark

Meta

closed

Reference only

28.7 index

#30

DeepSeek V4 Flash (High)

deepseek-v4-flash-high

DeepSeek

open

Estimated reference

28.2 index

#31

Qwen3.6 Plus

qwen3-6-plus

Alibaba Cloud

closed

Reference only

27.6 index

#32

GPT-5.4 nano

gpt.5.4.nano

OpenAI

closed

Reference only

27.5 index

#33

Nemotron 3 Ultra

nemotron-3-ultra-550b

NVIDIA

open

Estimated reference

27.4 index

#34

Qwen3.6 27B

qwen3.6-27b

Alibaba Cloud

open

Estimated reference

27.0 index

#35

Gemini 3.5 Flash-Lite

gemini-3.5-flash-lite

Google

closed

Estimated reference

26.8 index

#36

GPT-5 (high)

gpt-5-high

OpenAI

closed

Estimated reference

25.7 index

#37

MiniMax M2.7

minimax-m2-7

MiniMax

open

Reference only

25.6 index

#38

GLM-4.7

glm-4.7

Z.AI

open

Reference only

25.4 index

#39

Grok 4.3

grok-4.3

xAI

closed

Reference only

24.1 index

#40

Kimi K2.5

kimi-k2.5

Moonshot AI

—

Reference only

21.7 index

#41

Kimi K2.5 (Reasoning)

kimi-k2-5-reasoning

Moonshot AI

closed

Estimated reference

21.7 index

#42

Step 3.7 Flash

step-3-7-flash

StepFun

open

Estimated reference

21.5 index

#43

Qwen3.6-35B-A3B

qwen3-6-35b-a3b

Alibaba Cloud

open

Estimated reference

21.4 index

#44

Gemini 3.1 Pro

gemini-3-1-pro

Google

closed

Estimated reference

21.4 index

#45

GPT-5.1

gpt.5.1

OpenAI

closed

Estimated reference

21.0 index

#46

Qwen3.7-Plus

qwen3.7-plus

Alibaba Cloud

—

Reference only

20.8 index

#47

Qwen3.5-122B-A10B

qwen3-5-122b-a10b

Alibaba Cloud

open

Reference only

20.7 index

#48

Qwen3.5 397B

qwen3.5-397b-a17b

Alibaba Cloud

open

Estimated reference

19.9 index

#49

Qwen3.5 397B (Reasoning)

qwen3-5-397b-reasoning

Alibaba Cloud

open

Estimated reference

19.9 index

#50

Mistral Medium 3.5 128B

mistral-medium-3-5-128b

Mistral AI

open

Estimated reference

19 index

#51

Gemma 4 31B

gemma-4-31b

Google

open

Reference only

14.4 index

#52

GPT-OSS 120B

gpt-oss-120b

OpenAI

open

Reference only

13.2 index

#53

MiMo-V2-Flash

mimo-v2-flash

Xiaomi

open

Reference only

12.0 index

#54

Gemma 4 26B A4B

gemma-4-26b-a4b

Google

open

Reference only

11.0 index

#55

Command A+

command-a-plus

Cohere

open

Estimated reference

9.2 index

#56

Gemini 2.5 Pro

gemini-2.5-pro

Google

closed

Reference only

7.1 index

#57

Gemini 3.1 Flash-Lite

gemini-3.1-flash-lite

Google

closed

Reference only

6.2 index

#58

Mistral Large 3

mistral-large-2512

Mistral AI

open

Reference only

5.5 index

#59

Mistral Small 4

mistral-small-2603

Mistral AI

open

Estimated reference

4.7 index

#60

Mistral Small 4 (Reasoning)

mistral-small-4-reasoning

Mistral AI

open

Estimated reference

4.7 index

#61

GPT-OSS 20B

gpt-oss-20b

OpenAI

open

Reference only

3.1 index

#62

Ling 2.6 Flash

ling-2-6-flash

InclusionAI

open

Estimated reference

2.3 index

#63

Nemotron 3 Nano 30B

nemotron-3-nano-30b

NVIDIA

open

Estimated reference

2.0 index

#64

GPT-4.1 mini

gpt-4-1-mini

OpenAI

closed

Estimated reference

1.7 index

#65

DeepSeek V3

deepseek-v3

DeepSeek

open

Reference only

1.6 index

#66

Llama 4 Maverick

llama-4-maverick

Meta

open

Reference only

1.3 index

#67

GPT-4.1 nano

gpt-4-1-nano

OpenAI

closed

Estimated reference

1.2 index

#68

Llama 4 Scout

llama-4-scout

Meta

open

Reference only

1.1 index

#69

GPT-4o mini

gpt-4o-mini

OpenAI

closed

Reference only

1.0 index

#70

Gemma 3 27B

gemma-3-27b

Google

open

Reference only

0.3 index

Definition and scoring

Organisation

Artificial Analysis

What does Artificial Analysis Agentic Index measure?

A display-only Artificial Analysis agentic index.

Which model scores highest on Artificial Analysis Agentic Index?

GPT-5.6 Sol by OpenAI currently leads with 54 index.

How many models are evaluated on Artificial Analysis Agentic Index?

70 models in the LuminaBench cohort have a qualifying score on this benchmark.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

Search LUMINA BENCH

Navigation

Artificial Analysis Agentic Index

Leaderboard · 70 models

GPT-5.6 Sol

Claude Fable 5

Kimi K3

See the field.