Artificial Analysis Omniscience Accuracy leaderboard & scores

Accessible data for Artificial Analysis Omniscience Accuracy leaderboard
Model	Rank	Provider	Score
Claude Fable 5	#1	Anthropic	61.4%
GPT-5.6 Sol	#2	OpenAI	58.5%
GPT-5.5	#3	OpenAI	56.9%
Gemini 3 Pro	#4	Google	55.9%
Gemini 3.1 Pro	#5	Google	55.3%
Grok 4.5	#6	xAI	52.1%
Gemini 3.5 Flash	#7	Google	51.9%
GPT-5.3-Codex	#8	OpenAI	51.8%
Gemini 3.6 Flash	#9	Google	50.2%
GPT-5.4	#10	OpenAI	50%
Claude Opus 4.8	#11	Anthropic	46.6%
Claude Opus 4.6 (Adaptive)	#12	Anthropic	46.4%
Kimi K3	#13	Moonshot AI	46%
GPT-5.6 Terra	#14	OpenAI	45.9%
Claude Opus 4.7 (Adaptive)	#15	Anthropic	45.8%
Claude Opus 4.5 Thinking	#16	Anthropic	45.7%
Gemini 3 Flash	#17	Google	45.5%
Claude Opus 4.6	#18	Anthropic	45.2%
Muse Spark	#19	Meta	44.6%
GPT-5.2	#20	OpenAI	43.8%

Model

Rank

Provider

Score

Claude Fable 5

Anthropic

61.4%

GPT-5.6 Sol

OpenAI

58.5%

GPT-5.5

OpenAI

56.9%

Gemini 3 Pro

Google

55.9%

Gemini 3.1 Pro

Google

55.3%

Grok 4.5

xAI

52.1%

Gemini 3.5 Flash

Google

51.9%

GPT-5.3-Codex

OpenAI

51.8%

Gemini 3.6 Flash

Google

50.2%

GPT-5.4

#10

OpenAI

50%

Claude Opus 4.8

#11

Anthropic

46.6%

Claude Opus 4.6 (Adaptive)

#12

Anthropic

46.4%

Kimi K3

#13

Moonshot AI

46%

GPT-5.6 Terra

#14

OpenAI

45.9%

Claude Opus 4.7 (Adaptive)

#15

Anthropic

45.8%

Claude Opus 4.5 Thinking

#16

Anthropic

45.7%

Gemini 3 Flash

#17

Google

45.5%

Claude Opus 4.6

#18

Anthropic

45.2%

Muse Spark

#19

Meta

44.6%

GPT-5.2

#20

OpenAI

43.8%

Artificial Analysis Omniscience Accuracy leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Claude Fable 5 claude-fable-5	Anthropic	closed	Reference only	61.4%
#2	GPT-5.6 Sol gpt-5.6-sol	OpenAI	closed	Reference only	58.5%
#3	GPT-5.5 gpt-5.5	OpenAI	closed	Estimated reference	56.9%
#4	Gemini 3 Pro gemini-3-pro	Google	closed	Reference only	55.9%
#5	Gemini 3.1 Pro gemini-3-1-pro	Google	closed	Estimated reference	55.3%
#6	Grok 4.5 grok-4.5	xAI	closed	Reference only	52.1%
#7	Gemini 3.5 Flash gemini-3.5-flash	Google	closed	Estimated reference	51.9%
#8	GPT-5.3-Codex gpt-5.3-codex	OpenAI	closed	Reference only	51.8%
#9	Gemini 3.6 Flash gemini-3.6-flash	Google	closed	Estimated reference	50.2%
#10	GPT-5.4 gpt-5.4	OpenAI	closed	Reference only	50%
#11	Claude Opus 4.8 claude-opus-4-8	Anthropic	closed	Reference only	46.6%
#12	Claude Opus 4.6 (Adaptive) claude-opus-4-6-thinking	Anthropic	closed	Estimated reference	46.4%
#13	Kimi K3 kimi-k3	Moonshot AI	closed	Reference only	46%
#14	GPT-5.6 Terra gpt-5.6-terra	OpenAI	closed	Estimated reference	45.9%
#15	Claude Opus 4.7 (Adaptive) claude-opus-4-7-max	Anthropic	closed	Estimated reference	45.8%
#16	Claude Opus 4.5 Thinking claude-opus-4-5-thinking	Anthropic	closed	Estimated reference	45.7%
#17	Gemini 3 Flash gemini-3-flash	Google	closed	Reference only	45.5%
#18	Claude Opus 4.6 claude-opus-4-6	Anthropic	closed	Reference only	45.2%
#19	Muse Spark muse-spark	Meta	closed	Reference only	44.6%
#20	GPT-5.2 gpt-5.2	OpenAI	closed	Estimated reference	43.8%
#21	Claude Opus 4.7 claude-opus-4-7	Anthropic	closed	Reference only	43.5%
#22	DeepSeek V4 Pro (Max) deepseek-v4-pro-max	DeepSeek	open	Estimated reference	43.3%
#23	DeepSeek V4 Pro (High) deepseek-v4-pro-high	DeepSeek	open	Estimated reference	41.8%
#24	GPT-5.6 Luna gpt-5.6-luna	OpenAI	closed	Estimated reference	41.5%
#25	Grok 4 grok-4	xAI	closed	Reference only	41.4%
#26	Claude Opus 4.5 claude-opus-4-5	Anthropic	closed	Reference only	40.7%
#27	GPT-5 (high) gpt-5-high	OpenAI	closed	Estimated reference	40.7%
#28	GPT-5.2 Codex gpt-5.2-codex	OpenAI	closed	Reference only	40.7%
#29	Muse Spark 1.1 muse-spark-1-1	Meta	closed	Reference only	40.6%
#30	Inkling inkling	Thinking Machines Lab	open	Reference only	40%
#31	GPT-5.1-Codex gpt-5-1-codex	OpenAI	closed	Estimated reference	39.2%
#32	GPT-5.1-Codex-Max gpt-5-1-codex-max	OpenAI	closed	Estimated reference	39.2%
#33	Gemini 2.5 Pro gemini-2.5-pro	Google	closed	Reference only	39%
#34	GPT-5 (medium) gpt-5-medium	OpenAI	closed	Reference only	38.9%
#35	Kimi K2.7 Code kimi-k2.7-code	Moonshot AI	open	Estimated reference	38.6%
#36	o3 o3	OpenAI	closed	Reference only	38.4%
#37	Claude Sonnet 5 claude-sonnet-5	Anthropic	closed	Estimated reference	38.3%
#38	Claude Sonnet 4.6 claude-sonnet-4-6	Anthropic	closed	Reference only	38%
#39	Qwen 3.6 Max (preview) qwen3-6-max-preview	Alibaba Cloud	closed	Reference only	37.7%
#40	GPT-5.1 gpt.5.1	OpenAI	closed	Estimated reference	37.6%
#41	GPT-5.4 mini gpt-5.4-mini	OpenAI	closed	Estimated reference	37.5%
#42	DeepSeek V4 Flash (Max) deepseek-v4-flash-max	DeepSeek	open	Estimated reference	37.2%
#43	Gemini 3.1 Flash-Lite gemini-3.1-flash-lite	Google	closed	Reference only	36.4%
#44	DeepSeek V4 Flash (High) deepseek-v4-flash-high	DeepSeek	open	Estimated reference	35.5%
#45	o1 o1	OpenAI	closed	Estimated reference	34.7%
#46	Grok 4.3 grok-4.3	xAI	closed	Reference only	34.6%
#47	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	34.3%
#48	Kimi K2.5 (Reasoning) kimi-k2-5-reasoning	Moonshot AI	closed	Estimated reference	34.3%
#49	Kimi K2.6 kimi-k2.6	Moonshot AI	open	Estimated reference	32.8%
#50	Hy3 hy3	Tencent	open	Estimated reference	31.5%
#51	Hy3 Preview hy3-preview	Tencent	open	Estimated reference	31.5%
#52	Qwen3.5 397B qwen3.5-397b-a17b	Alibaba Cloud	open	Estimated reference	31.4%
#53	Qwen3.5 397B (Reasoning) qwen3-5-397b-reasoning	Alibaba Cloud	open	Estimated reference	31.4%
#54	DeepSeek-R1 deepseek-r1	DeepSeek	open	Reference only	31%
#55	Gemini 3.5 Flash-Lite gemini-3.5-flash-lite	Google	closed	Estimated reference	30.3%
#56	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	30.1%
#57	GLM-4.7 glm-4.7	Z.AI	open	Reference only	29.3%
#58	GLM-5V-Turbo glm-5v-turbo	Z.AI	closed	Reference only	29.1%
#59	GLM-5-Turbo glm-5-turbo	Z.AI	closed	Reference only	29%
#60	DeepSeek V3.1 (Reasoning) deepseek-v3-1-reasoning	DeepSeek	open	Reference only	28.8%
#61	GLM-5 glm-5	Z.AI	open	Reference only	26.9%
#62	Kimi K2 kimi-k2	Moonshot AI	closed	Reference only	26.8%
#63	MiMo-V2-Pro mimo-v2-pro	Xiaomi	closed	Reference only	26.8%
#64	Gemini 2.5 Flash gemini-2.5-flash	Google	closed	Reference only	26.5%
#65	Qwen3.6 Plus qwen3-6-plus	Alibaba Cloud	closed	Reference only	26.2%
#66	MiniMax M2.7 minimax-m2-7	MiniMax	open	Reference only	26.1%
#67	DeepSeek V3 deepseek-v3	DeepSeek	open	Reference only	25.4%
#68	GPT-5.4 nano gpt.5.4.nano	OpenAI	closed	Reference only	25.4%
#69	Step 3.7 Flash step-3-7-flash	StepFun	open	Estimated reference	25.4%
#70	Grok 4.1 Fast (Reasoning) grok-4-1-fast-reasoning	xAI	closed	Reference only	25.3%
#71	GLM-5.2 glm-5-2	Z.AI	open	Estimated reference	25.1%
#72	Mistral Medium 3.5 128B mistral-medium-3-5-128b	Mistral AI	open	Estimated reference	25.1%
#73	Qwen3.5-122B-A10B qwen3-5-122b-a10b	Alibaba Cloud	open	Reference only	24.7%
#74	Qwen3 Max qwen3-max	Alibaba Cloud	closed	Estimated reference	24.4%
#75	Llama 4 Maverick llama-4-maverick	Meta	open	Reference only	24.3%
#76	DeepSeek V3.2 deepseek-v3.2	DeepSeek	open	Reference only	24.2%
#77	GLM-5.1 glm-5-1	Z.AI	open	Reference only	24.2%
#78	GPT-4.1 gpt-4-1	OpenAI	closed	Reference only	24.2%
#79	Mistral Large 3 mistral-large-2512	Mistral AI	open	Reference only	24.1%
#80	Grok Code Fast 1 grok-code-fast-1	xAI	closed	Reference only	23.8%
#81	DeepSeek V3.1 deepseek-v3-1	DeepSeek	open	Reference only	23.1%
#82	Trinity-Large-Preview trinity-large-preview	Arcee AI	open	Estimated reference	22.8%
#83	Trinity-Large-Thinking trinity-large-thinking	Arcee AI	open	Reference only	22.8%
#84	Grok 4 Fast (Reasoning) grok-4-fast-reasoning	xAI	closed	Reference only	22.6%
#85	MiMo-V2.5-Pro mimo-v2-5-pro	Xiaomi	closed	Reference only	22.6%
#86	Claude 4 Sonnet claude-4-sonnet	Anthropic	closed	Reference only	22.4%
#87	Llama 3.1 405B llama-3-1-405b	Meta	open	Estimated reference	22.3%
#88	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	22.2%
#89	Mistral Small 4 mistral-small-2603	Mistral AI	open	Estimated reference	22.1%
#90	Mistral Small 4 (Reasoning) mistral-small-4-reasoning	Mistral AI	open	Estimated reference	22.1%
#91	Nemotron 3 Ultra nemotron-3-ultra-550b	NVIDIA	open	Estimated reference	21.6%
#92	GPT-OSS 120B gpt-oss-120b	OpenAI	open	Reference only	21.5%
#93	Qwen3.5 27B qwen3.5-27b	Alibaba Cloud	open	Reference only	21%
#94	GLM-4.6 glm-4.6	Z.AI	open	Reference only	20.8%
#95	Qwen3.5-35B-A3B qwen3-5-35b-a3b	Alibaba Cloud	open	Reference only	20.5%
#96	Mistral Large 2 mistral-large-2	Mistral AI	closed	Estimated reference	20.1%
#97	Gemma 4 31B gemma-4-31b	Google	open	Reference only	19.9%
#98	Nemotron Ultra 253B nemotron-ultra-253b	NVIDIA	open	Estimated reference	19.9%
#99	GPT-4o gpt-4o	OpenAI	closed	Reference only	19.7%
#100	Qwen3.6 27B qwen3.6-27b	Alibaba Cloud	open	Estimated reference	19.2%
#101	Qwen3.6-35B-A3B qwen3-6-35b-a3b	Alibaba Cloud	open	Estimated reference	18.9%
#102	MiMo-V2-Omni mimo-v2-omni	Xiaomi	closed	Reference only	18.7%
#103	Mistral Medium 3 mistral-medium-3	Mistral AI	closed	Estimated reference	18.3%
#104	Gemma 4 26B A4B gemma-4-26b-a4b	Google	open	Reference only	18.2%
#105	Sarvam 105B sarvam-105b	Sarvam	open	Estimated reference	17.6%
#106	GPT-4.1 mini gpt-4-1-mini	OpenAI	closed	Estimated reference	17.5%
#107	Claude 3 Haiku claude-3-haiku	Anthropic	closed	Reference only	17.2%
#108	Nemotron 3 Nano 30B nemotron-3-nano-30b	NVIDIA	open	Estimated reference	17.1%
#109	Grok 4.1 Fast grok-4-1-fast	xAI	closed	Reference only	17%
#110	Nova Pro nova-pro	Amazon	closed	Reference only	17%
#111	K-Exaone k-exaone	LG AI Research	closed	Estimated reference	16.5%
#112	Gemma 4 12B gemma-4-12b	Google	open	Estimated reference	16%
#113	Solar Pro 2 solar-pro-2	Upstage	closed	Estimated reference	15.6%
#114	GLM-4.5-Air glm-4-5-air	Z.AI	closed	Reference only	15.5%
#115	GPT-OSS 20B gpt-oss-20b	OpenAI	open	Reference only	15.5%
#116	Ling 2.6 Flash ling-2-6-flash	InclusionAI	open	Estimated reference	15.4%
#117	MiMo-V2-Flash mimo-v2-flash	Xiaomi	open	Reference only	15.2%
#118	MiniMax M3 MiniMax-M3	MiniMax	—	Reference only	15%
#119	Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b	NVIDIA	open	Estimated reference	14.8%
#120	Llama 4 Scout llama-4-scout	Meta	open	Reference only	14.6%
#121	GPT-4.1 nano gpt-4-1-nano	OpenAI	closed	Estimated reference	13.3%
#122	Phi-4 phi-4	Microsoft	open	Reference only	13.2%
#123	Sarvam 30B sarvam-30b	Sarvam	open	Estimated reference	12.7%
#124	Gemma 3 27B gemma-3-27b	Google	open	Reference only	12.5%
#125	Exaone 4.0 32B exaone-4-0-32b	LG AI Research	open	Estimated reference	10.4%
#126	LFM2.5-8B-A1B lfm2-5-8b-a1b	LiquidAI	open	Estimated reference	9.4%
#127	Command A+ command-a-plus	Cohere	open	Estimated reference	8.9%
#128	Gemma 4 E4B gemma-4-e4b	Google	open	Estimated reference	8.6%
#129	Gemma 4 E2B gemma-4-e2b	Google	open	Estimated reference	6.7%
#130	Granite-4.0-1B granite-4-0-1b	IBM	open	Estimated reference	6.1%
#131	Granite-4.0-H-1B granite-4-0-h-1b	IBM	open	Estimated reference	5.3%
#132	LFM2.5-VL-1.6B-Extract lfm2-5-vl-1-6b-extract	LiquidAI	open	Estimated reference	5.2%
#133	Exaone 4.0 1.2B exaone-4-0-1-2b	LG AI Research	open	Estimated reference	4.7%
#134	Granite-4.0-H-350M granite-4-0-h-350m	IBM	open	Estimated reference	3.7%
#135	Granite-4.0-350M granite-4-0-350m	IBM	open	Estimated reference	3.2%

Rank

Model

Provider

License

Evidence use

Score

Claude Fable 5

claude-fable-5

Anthropic

closed

Reference only

61.4%

GPT-5.6 Sol

gpt-5.6-sol

OpenAI

closed

Reference only

58.5%

GPT-5.5

gpt-5.5

OpenAI

closed

Estimated reference

56.9%

Gemini 3 Pro

gemini-3-pro

Google

closed

Reference only

55.9%

Gemini 3.1 Pro

gemini-3-1-pro

Google

closed

Estimated reference

55.3%

Grok 4.5

grok-4.5

xAI

closed

Reference only

52.1%

Gemini 3.5 Flash

gemini-3.5-flash

Google

closed

Estimated reference

51.9%

GPT-5.3-Codex

gpt-5.3-codex

OpenAI

closed

Reference only

51.8%

Gemini 3.6 Flash

gemini-3.6-flash

Google

closed

Estimated reference

50.2%

#10

GPT-5.4

gpt-5.4

OpenAI

closed

Reference only

50%

#11

Claude Opus 4.8

claude-opus-4-8

Anthropic

closed

Reference only

46.6%

#12

Claude Opus 4.6 (Adaptive)

claude-opus-4-6-thinking

Anthropic

closed

Estimated reference

46.4%

#13

Kimi K3

kimi-k3

Moonshot AI

closed

Reference only

46%

#14

GPT-5.6 Terra

gpt-5.6-terra

OpenAI

closed

Estimated reference

45.9%

#15

Claude Opus 4.7 (Adaptive)

claude-opus-4-7-max

Anthropic

closed

Estimated reference

45.8%

#16

Claude Opus 4.5 Thinking

claude-opus-4-5-thinking

Anthropic

closed

Estimated reference

45.7%

#17

Gemini 3 Flash

gemini-3-flash

Google

closed

Reference only

45.5%

#18

Claude Opus 4.6

claude-opus-4-6

Anthropic

closed

Reference only

45.2%

#19

Muse Spark

muse-spark

Meta

closed

Reference only

44.6%

#20

GPT-5.2

gpt-5.2

OpenAI

closed

Estimated reference

43.8%

#21

Claude Opus 4.7

claude-opus-4-7

Anthropic

closed

Reference only

43.5%

#22

DeepSeek V4 Pro (Max)

deepseek-v4-pro-max

DeepSeek

open

Estimated reference

43.3%

#23

DeepSeek V4 Pro (High)

deepseek-v4-pro-high

DeepSeek

open

Estimated reference

41.8%

#24

GPT-5.6 Luna

gpt-5.6-luna

OpenAI

closed

Estimated reference

41.5%

#25

Grok 4

grok-4

xAI

closed

Reference only

41.4%

#26

Claude Opus 4.5

claude-opus-4-5

Anthropic

closed

Reference only

40.7%

#27

GPT-5 (high)

gpt-5-high

OpenAI

closed

Estimated reference

40.7%

#28

GPT-5.2 Codex

gpt-5.2-codex

OpenAI

closed

Reference only

40.7%

#29

Muse Spark 1.1

muse-spark-1-1

Meta

closed

Reference only

40.6%

#30

Inkling

inkling

Thinking Machines Lab

open

Reference only

40%

#31

GPT-5.1-Codex

gpt-5-1-codex

OpenAI

closed

Estimated reference

39.2%

#32

GPT-5.1-Codex-Max

gpt-5-1-codex-max

OpenAI

closed

Estimated reference

39.2%

#33

Gemini 2.5 Pro

gemini-2.5-pro

Google

closed

Reference only

39%

#34

GPT-5 (medium)

gpt-5-medium

OpenAI

closed

Reference only

38.9%

#35

Kimi K2.7 Code

kimi-k2.7-code

Moonshot AI

open

Estimated reference

38.6%

#36

OpenAI

closed

Reference only

38.4%

#37

Claude Sonnet 5

claude-sonnet-5

Anthropic

closed

Estimated reference

38.3%

#38

Claude Sonnet 4.6

claude-sonnet-4-6

Anthropic

closed

Reference only

38%

#39

Qwen 3.6 Max (preview)

qwen3-6-max-preview

Alibaba Cloud

closed

Reference only

37.7%

#40

GPT-5.1

gpt.5.1

OpenAI

closed

Estimated reference

37.6%

#41

GPT-5.4 mini

gpt-5.4-mini

OpenAI

closed

Estimated reference

37.5%

#42

DeepSeek V4 Flash (Max)

deepseek-v4-flash-max

DeepSeek

open

Estimated reference

37.2%

#43

Gemini 3.1 Flash-Lite

gemini-3.1-flash-lite

Google

closed

Reference only

36.4%

#44

DeepSeek V4 Flash (High)

deepseek-v4-flash-high

DeepSeek

open

Estimated reference

35.5%

#45

OpenAI

closed

Estimated reference

34.7%

#46

Grok 4.3

grok-4.3

xAI

closed

Reference only

34.6%

#47

Kimi K2.5

kimi-k2.5

Moonshot AI

—

Reference only

34.3%

#48

Kimi K2.5 (Reasoning)

kimi-k2-5-reasoning

Moonshot AI

closed

Estimated reference

34.3%

#49

Kimi K2.6

kimi-k2.6

Moonshot AI

open

Estimated reference

32.8%

#50

Hy3

hy3

Tencent

open

Estimated reference

31.5%

#51

Hy3 Preview

hy3-preview

Tencent

open

Estimated reference

31.5%

#52

Qwen3.5 397B

qwen3.5-397b-a17b

Alibaba Cloud

open

Estimated reference

31.4%

#53

Qwen3.5 397B (Reasoning)

qwen3-5-397b-reasoning

Alibaba Cloud

open

Estimated reference

31.4%

#54

DeepSeek-R1

deepseek-r1

DeepSeek

open

Reference only

31%

#55

Gemini 3.5 Flash-Lite

gemini-3.5-flash-lite

Google

closed

Estimated reference

30.3%

#56

Qwen3.7-Max

qwen3.7-max

Alibaba Cloud

—

Reference only

30.1%

#57

GLM-4.7

glm-4.7

Z.AI

open

Reference only

29.3%

#58

GLM-5V-Turbo

glm-5v-turbo

Z.AI

closed

Reference only

29.1%

#59

GLM-5-Turbo

glm-5-turbo

Z.AI

closed

Reference only

29%

#60

DeepSeek V3.1 (Reasoning)

deepseek-v3-1-reasoning

DeepSeek

open

Reference only

28.8%

#61

GLM-5

glm-5

Z.AI

open

Reference only

26.9%

#62

Kimi K2

kimi-k2

Moonshot AI

closed

Reference only

26.8%

#63

MiMo-V2-Pro

mimo-v2-pro

Xiaomi

closed

Reference only

26.8%

#64

Gemini 2.5 Flash

gemini-2.5-flash

Google

closed

Reference only

26.5%

#65

Qwen3.6 Plus

qwen3-6-plus

Alibaba Cloud

closed

Reference only

26.2%

#66

MiniMax M2.7

minimax-m2-7

MiniMax

open

Reference only

26.1%

#67

DeepSeek V3

deepseek-v3

DeepSeek

open

Reference only

25.4%

#68

GPT-5.4 nano

gpt.5.4.nano

OpenAI

closed

Reference only

25.4%

#69

Step 3.7 Flash

step-3-7-flash

StepFun

open

Estimated reference

25.4%

#70

Grok 4.1 Fast (Reasoning)

grok-4-1-fast-reasoning

xAI

closed

Reference only

25.3%

#71

GLM-5.2

glm-5-2

Z.AI

open

Estimated reference

25.1%

#72

Mistral Medium 3.5 128B

mistral-medium-3-5-128b

Mistral AI

open

Estimated reference

25.1%

#73

Qwen3.5-122B-A10B

qwen3-5-122b-a10b

Alibaba Cloud

open

Reference only

24.7%

#74

Qwen3 Max

qwen3-max

Alibaba Cloud

closed

Estimated reference

24.4%

#75

Llama 4 Maverick

llama-4-maverick

Meta

open

Reference only

24.3%

#76

DeepSeek V3.2

deepseek-v3.2

DeepSeek

open

Reference only

24.2%

#77

GLM-5.1

glm-5-1

Z.AI

open

Reference only

24.2%

#78

GPT-4.1

gpt-4-1

OpenAI

closed

Reference only

24.2%

#79

Mistral Large 3

mistral-large-2512

Mistral AI

open

Reference only

24.1%

#80

Grok Code Fast 1

grok-code-fast-1

xAI

closed

Reference only

23.8%

#81

DeepSeek V3.1

deepseek-v3-1

DeepSeek

open

Reference only

23.1%

#82

Trinity-Large-Preview

trinity-large-preview

Arcee AI

open

Estimated reference

22.8%

#83

Trinity-Large-Thinking

trinity-large-thinking

Arcee AI

open

Reference only

22.8%

#84

Grok 4 Fast (Reasoning)

grok-4-fast-reasoning

xAI

closed

Reference only

22.6%

#85

MiMo-V2.5-Pro

mimo-v2-5-pro

Xiaomi

closed

Reference only

22.6%

#86

Claude 4 Sonnet

claude-4-sonnet

Anthropic

closed

Reference only

22.4%

#87

Llama 3.1 405B

llama-3-1-405b

Meta

open

Estimated reference

22.3%

#88

Qwen3.7-Plus

qwen3.7-plus

Alibaba Cloud

—

Reference only

22.2%

#89

Mistral Small 4

mistral-small-2603

Mistral AI

open

Estimated reference

22.1%

#90

Mistral Small 4 (Reasoning)

mistral-small-4-reasoning

Mistral AI

open

Estimated reference

22.1%

#91

Nemotron 3 Ultra

nemotron-3-ultra-550b

NVIDIA

open

Estimated reference

21.6%

#92

GPT-OSS 120B

gpt-oss-120b

OpenAI

open

Reference only

21.5%

#93

Qwen3.5 27B

qwen3.5-27b

Alibaba Cloud

open

Reference only

21%

#94

GLM-4.6

glm-4.6

Z.AI

open

Reference only

20.8%

#95

Qwen3.5-35B-A3B

qwen3-5-35b-a3b

Alibaba Cloud

open

Reference only

20.5%

#96

Mistral Large 2

mistral-large-2

Mistral AI

closed

Estimated reference

20.1%

#97

Gemma 4 31B

gemma-4-31b

Google

open

Reference only

19.9%

#98

Nemotron Ultra 253B

nemotron-ultra-253b

NVIDIA

open

Estimated reference

19.9%

#99

GPT-4o

gpt-4o

OpenAI

closed

Reference only

19.7%

#100

Qwen3.6 27B

qwen3.6-27b

Alibaba Cloud

open

Estimated reference

19.2%

#101

Qwen3.6-35B-A3B

qwen3-6-35b-a3b

Alibaba Cloud

open

Estimated reference

18.9%

#102

MiMo-V2-Omni

mimo-v2-omni

Xiaomi

closed

Reference only

18.7%

#103

Mistral Medium 3

mistral-medium-3

Mistral AI

closed

Estimated reference

18.3%

#104

Gemma 4 26B A4B

gemma-4-26b-a4b

Google

open

Reference only

18.2%

#105

Sarvam 105B

sarvam-105b

Sarvam

open

Estimated reference

17.6%

#106

GPT-4.1 mini

gpt-4-1-mini

OpenAI

closed

Estimated reference

17.5%

#107

Claude 3 Haiku

claude-3-haiku

Anthropic

closed

Reference only

17.2%

#108

Nemotron 3 Nano 30B

nemotron-3-nano-30b

NVIDIA

open

Estimated reference

17.1%

#109

Grok 4.1 Fast

grok-4-1-fast

xAI

closed

Reference only

17%

#110

Nova Pro

nova-pro

Amazon

closed

Reference only

17%

#111

K-Exaone

k-exaone

LG AI Research

closed

Estimated reference

16.5%

#112

Gemma 4 12B

gemma-4-12b

Google

open

Estimated reference

16%

#113

Solar Pro 2

solar-pro-2

Upstage

closed

Estimated reference

15.6%

#114

GLM-4.5-Air

glm-4-5-air

Z.AI

closed

Reference only

15.5%

#115

GPT-OSS 20B

gpt-oss-20b

OpenAI

open

Reference only

15.5%

#116

Ling 2.6 Flash

ling-2-6-flash

InclusionAI

open

Estimated reference

15.4%

#117

MiMo-V2-Flash

mimo-v2-flash

Xiaomi

open

Reference only

15.2%

#118

MiniMax M3

MiniMax-M3

MiniMax

—

Reference only

15%

#119

Nemotron 3 Nano Omni 30B A3B

nemotron-3-nano-omni-30b-a3b

NVIDIA

open

Estimated reference

14.8%

#120

Llama 4 Scout

llama-4-scout

Meta

open

Reference only

14.6%

#121

GPT-4.1 nano

gpt-4-1-nano

OpenAI

closed

Estimated reference

13.3%

#122

Phi-4

phi-4

Microsoft

open

Reference only

13.2%

#123

Sarvam 30B

sarvam-30b

Sarvam

open

Estimated reference

12.7%

#124

Gemma 3 27B

gemma-3-27b

Google

open

Reference only

12.5%

#125

Exaone 4.0 32B

exaone-4-0-32b

LG AI Research

open

Estimated reference

10.4%

#126

LFM2.5-8B-A1B

lfm2-5-8b-a1b

LiquidAI

open

Estimated reference

9.4%

#127

Command A+

command-a-plus

Cohere

open

Estimated reference

8.9%

#128

Gemma 4 E4B

gemma-4-e4b

Google

open

Estimated reference

8.6%

#129

Gemma 4 E2B

gemma-4-e2b

Google

open

Estimated reference

6.7%

#130

Granite-4.0-1B

granite-4-0-1b

IBM

open

Estimated reference

6.1%

#131

Granite-4.0-H-1B

granite-4-0-h-1b

IBM

open

Estimated reference

5.3%

#132

LFM2.5-VL-1.6B-Extract

lfm2-5-vl-1-6b-extract

LiquidAI

open

Estimated reference

5.2%

#133

Exaone 4.0 1.2B

exaone-4-0-1-2b

LG AI Research

open

Estimated reference

4.7%

#134

Granite-4.0-H-350M

granite-4-0-h-350m

IBM

open

Estimated reference

3.7%

#135

Granite-4.0-350M

granite-4-0-350m

IBM

open

Estimated reference

3.2%

Definition and scoring

Organisation

Artificial Analysis

What does Artificial Analysis Omniscience Accuracy measure?

A display-only Artificial Analysis knowledge metric for the proportion of correctly answered questions.

Which model scores highest on Artificial Analysis Omniscience Accuracy?

Claude Fable 5 by Anthropic currently leads with 61.4%.

How many models are evaluated on Artificial Analysis Omniscience Accuracy?

135 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 Omniscience Accuracy leaderboard
Model	Rank	Provider	Score
Claude Fable 5	#1	Anthropic	61.4%
GPT-5.6 Sol	#2	OpenAI	58.5%
GPT-5.5	#3	OpenAI	56.9%
Gemini 3 Pro	#4	Google	55.9%
Gemini 3.1 Pro	#5	Google	55.3%
Grok 4.5	#6	xAI	52.1%
Gemini 3.5 Flash	#7	Google	51.9%
GPT-5.3-Codex	#8	OpenAI	51.8%
Gemini 3.6 Flash	#9	Google	50.2%
GPT-5.4	#10	OpenAI	50%
Claude Opus 4.8	#11	Anthropic	46.6%
Claude Opus 4.6 (Adaptive)	#12	Anthropic	46.4%
Kimi K3	#13	Moonshot AI	46%
GPT-5.6 Terra	#14	OpenAI	45.9%
Claude Opus 4.7 (Adaptive)	#15	Anthropic	45.8%
Claude Opus 4.5 Thinking	#16	Anthropic	45.7%
Gemini 3 Flash	#17	Google	45.5%
Claude Opus 4.6	#18	Anthropic	45.2%
Muse Spark	#19	Meta	44.6%
GPT-5.2	#20	OpenAI	43.8%

Model

Rank

Provider

Score

Claude Fable 5

Anthropic

61.4%

GPT-5.6 Sol

OpenAI

58.5%

GPT-5.5

OpenAI

56.9%

Gemini 3 Pro

Google

55.9%

Gemini 3.1 Pro

Google

55.3%

Grok 4.5

xAI

52.1%

Gemini 3.5 Flash

Google

51.9%

GPT-5.3-Codex

OpenAI

51.8%

Gemini 3.6 Flash

Google

50.2%

GPT-5.4

#10

OpenAI

50%

Claude Opus 4.8

#11

Anthropic

46.6%

Claude Opus 4.6 (Adaptive)

#12

Anthropic

46.4%

Kimi K3

#13

Moonshot AI

46%

GPT-5.6 Terra

#14

OpenAI

45.9%

Claude Opus 4.7 (Adaptive)

#15

Anthropic

45.8%

Claude Opus 4.5 Thinking

#16

Anthropic

45.7%

Gemini 3 Flash

#17

Google

45.5%

Claude Opus 4.6

#18

Anthropic

45.2%

Muse Spark

#19

Meta

44.6%

GPT-5.2

#20

OpenAI

43.8%

Artificial Analysis Omniscience Accuracy leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Claude Fable 5 claude-fable-5	Anthropic	closed	Reference only	61.4%
#2	GPT-5.6 Sol gpt-5.6-sol	OpenAI	closed	Reference only	58.5%
#3	GPT-5.5 gpt-5.5	OpenAI	closed	Estimated reference	56.9%
#4	Gemini 3 Pro gemini-3-pro	Google	closed	Reference only	55.9%
#5	Gemini 3.1 Pro gemini-3-1-pro	Google	closed	Estimated reference	55.3%
#6	Grok 4.5 grok-4.5	xAI	closed	Reference only	52.1%
#7	Gemini 3.5 Flash gemini-3.5-flash	Google	closed	Estimated reference	51.9%
#8	GPT-5.3-Codex gpt-5.3-codex	OpenAI	closed	Reference only	51.8%
#9	Gemini 3.6 Flash gemini-3.6-flash	Google	closed	Estimated reference	50.2%
#10	GPT-5.4 gpt-5.4	OpenAI	closed	Reference only	50%
#11	Claude Opus 4.8 claude-opus-4-8	Anthropic	closed	Reference only	46.6%
#12	Claude Opus 4.6 (Adaptive) claude-opus-4-6-thinking	Anthropic	closed	Estimated reference	46.4%
#13	Kimi K3 kimi-k3	Moonshot AI	closed	Reference only	46%
#14	GPT-5.6 Terra gpt-5.6-terra	OpenAI	closed	Estimated reference	45.9%
#15	Claude Opus 4.7 (Adaptive) claude-opus-4-7-max	Anthropic	closed	Estimated reference	45.8%
#16	Claude Opus 4.5 Thinking claude-opus-4-5-thinking	Anthropic	closed	Estimated reference	45.7%
#17	Gemini 3 Flash gemini-3-flash	Google	closed	Reference only	45.5%
#18	Claude Opus 4.6 claude-opus-4-6	Anthropic	closed	Reference only	45.2%
#19	Muse Spark muse-spark	Meta	closed	Reference only	44.6%
#20	GPT-5.2 gpt-5.2	OpenAI	closed	Estimated reference	43.8%
#21	Claude Opus 4.7 claude-opus-4-7	Anthropic	closed	Reference only	43.5%
#22	DeepSeek V4 Pro (Max) deepseek-v4-pro-max	DeepSeek	open	Estimated reference	43.3%
#23	DeepSeek V4 Pro (High) deepseek-v4-pro-high	DeepSeek	open	Estimated reference	41.8%
#24	GPT-5.6 Luna gpt-5.6-luna	OpenAI	closed	Estimated reference	41.5%
#25	Grok 4 grok-4	xAI	closed	Reference only	41.4%
#26	Claude Opus 4.5 claude-opus-4-5	Anthropic	closed	Reference only	40.7%
#27	GPT-5 (high) gpt-5-high	OpenAI	closed	Estimated reference	40.7%
#28	GPT-5.2 Codex gpt-5.2-codex	OpenAI	closed	Reference only	40.7%
#29	Muse Spark 1.1 muse-spark-1-1	Meta	closed	Reference only	40.6%
#30	Inkling inkling	Thinking Machines Lab	open	Reference only	40%
#31	GPT-5.1-Codex gpt-5-1-codex	OpenAI	closed	Estimated reference	39.2%
#32	GPT-5.1-Codex-Max gpt-5-1-codex-max	OpenAI	closed	Estimated reference	39.2%
#33	Gemini 2.5 Pro gemini-2.5-pro	Google	closed	Reference only	39%
#34	GPT-5 (medium) gpt-5-medium	OpenAI	closed	Reference only	38.9%
#35	Kimi K2.7 Code kimi-k2.7-code	Moonshot AI	open	Estimated reference	38.6%
#36	o3 o3	OpenAI	closed	Reference only	38.4%
#37	Claude Sonnet 5 claude-sonnet-5	Anthropic	closed	Estimated reference	38.3%
#38	Claude Sonnet 4.6 claude-sonnet-4-6	Anthropic	closed	Reference only	38%
#39	Qwen 3.6 Max (preview) qwen3-6-max-preview	Alibaba Cloud	closed	Reference only	37.7%
#40	GPT-5.1 gpt.5.1	OpenAI	closed	Estimated reference	37.6%
#41	GPT-5.4 mini gpt-5.4-mini	OpenAI	closed	Estimated reference	37.5%
#42	DeepSeek V4 Flash (Max) deepseek-v4-flash-max	DeepSeek	open	Estimated reference	37.2%
#43	Gemini 3.1 Flash-Lite gemini-3.1-flash-lite	Google	closed	Reference only	36.4%
#44	DeepSeek V4 Flash (High) deepseek-v4-flash-high	DeepSeek	open	Estimated reference	35.5%
#45	o1 o1	OpenAI	closed	Estimated reference	34.7%
#46	Grok 4.3 grok-4.3	xAI	closed	Reference only	34.6%
#47	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	34.3%
#48	Kimi K2.5 (Reasoning) kimi-k2-5-reasoning	Moonshot AI	closed	Estimated reference	34.3%
#49	Kimi K2.6 kimi-k2.6	Moonshot AI	open	Estimated reference	32.8%
#50	Hy3 hy3	Tencent	open	Estimated reference	31.5%
#51	Hy3 Preview hy3-preview	Tencent	open	Estimated reference	31.5%
#52	Qwen3.5 397B qwen3.5-397b-a17b	Alibaba Cloud	open	Estimated reference	31.4%
#53	Qwen3.5 397B (Reasoning) qwen3-5-397b-reasoning	Alibaba Cloud	open	Estimated reference	31.4%
#54	DeepSeek-R1 deepseek-r1	DeepSeek	open	Reference only	31%
#55	Gemini 3.5 Flash-Lite gemini-3.5-flash-lite	Google	closed	Estimated reference	30.3%
#56	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	30.1%
#57	GLM-4.7 glm-4.7	Z.AI	open	Reference only	29.3%
#58	GLM-5V-Turbo glm-5v-turbo	Z.AI	closed	Reference only	29.1%
#59	GLM-5-Turbo glm-5-turbo	Z.AI	closed	Reference only	29%
#60	DeepSeek V3.1 (Reasoning) deepseek-v3-1-reasoning	DeepSeek	open	Reference only	28.8%
#61	GLM-5 glm-5	Z.AI	open	Reference only	26.9%
#62	Kimi K2 kimi-k2	Moonshot AI	closed	Reference only	26.8%
#63	MiMo-V2-Pro mimo-v2-pro	Xiaomi	closed	Reference only	26.8%
#64	Gemini 2.5 Flash gemini-2.5-flash	Google	closed	Reference only	26.5%
#65	Qwen3.6 Plus qwen3-6-plus	Alibaba Cloud	closed	Reference only	26.2%
#66	MiniMax M2.7 minimax-m2-7	MiniMax	open	Reference only	26.1%
#67	DeepSeek V3 deepseek-v3	DeepSeek	open	Reference only	25.4%
#68	GPT-5.4 nano gpt.5.4.nano	OpenAI	closed	Reference only	25.4%
#69	Step 3.7 Flash step-3-7-flash	StepFun	open	Estimated reference	25.4%
#70	Grok 4.1 Fast (Reasoning) grok-4-1-fast-reasoning	xAI	closed	Reference only	25.3%
#71	GLM-5.2 glm-5-2	Z.AI	open	Estimated reference	25.1%
#72	Mistral Medium 3.5 128B mistral-medium-3-5-128b	Mistral AI	open	Estimated reference	25.1%
#73	Qwen3.5-122B-A10B qwen3-5-122b-a10b	Alibaba Cloud	open	Reference only	24.7%
#74	Qwen3 Max qwen3-max	Alibaba Cloud	closed	Estimated reference	24.4%
#75	Llama 4 Maverick llama-4-maverick	Meta	open	Reference only	24.3%
#76	DeepSeek V3.2 deepseek-v3.2	DeepSeek	open	Reference only	24.2%
#77	GLM-5.1 glm-5-1	Z.AI	open	Reference only	24.2%
#78	GPT-4.1 gpt-4-1	OpenAI	closed	Reference only	24.2%
#79	Mistral Large 3 mistral-large-2512	Mistral AI	open	Reference only	24.1%
#80	Grok Code Fast 1 grok-code-fast-1	xAI	closed	Reference only	23.8%
#81	DeepSeek V3.1 deepseek-v3-1	DeepSeek	open	Reference only	23.1%
#82	Trinity-Large-Preview trinity-large-preview	Arcee AI	open	Estimated reference	22.8%
#83	Trinity-Large-Thinking trinity-large-thinking	Arcee AI	open	Reference only	22.8%
#84	Grok 4 Fast (Reasoning) grok-4-fast-reasoning	xAI	closed	Reference only	22.6%
#85	MiMo-V2.5-Pro mimo-v2-5-pro	Xiaomi	closed	Reference only	22.6%
#86	Claude 4 Sonnet claude-4-sonnet	Anthropic	closed	Reference only	22.4%
#87	Llama 3.1 405B llama-3-1-405b	Meta	open	Estimated reference	22.3%
#88	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	22.2%
#89	Mistral Small 4 mistral-small-2603	Mistral AI	open	Estimated reference	22.1%
#90	Mistral Small 4 (Reasoning) mistral-small-4-reasoning	Mistral AI	open	Estimated reference	22.1%
#91	Nemotron 3 Ultra nemotron-3-ultra-550b	NVIDIA	open	Estimated reference	21.6%
#92	GPT-OSS 120B gpt-oss-120b	OpenAI	open	Reference only	21.5%
#93	Qwen3.5 27B qwen3.5-27b	Alibaba Cloud	open	Reference only	21%
#94	GLM-4.6 glm-4.6	Z.AI	open	Reference only	20.8%
#95	Qwen3.5-35B-A3B qwen3-5-35b-a3b	Alibaba Cloud	open	Reference only	20.5%
#96	Mistral Large 2 mistral-large-2	Mistral AI	closed	Estimated reference	20.1%
#97	Gemma 4 31B gemma-4-31b	Google	open	Reference only	19.9%
#98	Nemotron Ultra 253B nemotron-ultra-253b	NVIDIA	open	Estimated reference	19.9%
#99	GPT-4o gpt-4o	OpenAI	closed	Reference only	19.7%
#100	Qwen3.6 27B qwen3.6-27b	Alibaba Cloud	open	Estimated reference	19.2%
#101	Qwen3.6-35B-A3B qwen3-6-35b-a3b	Alibaba Cloud	open	Estimated reference	18.9%
#102	MiMo-V2-Omni mimo-v2-omni	Xiaomi	closed	Reference only	18.7%
#103	Mistral Medium 3 mistral-medium-3	Mistral AI	closed	Estimated reference	18.3%
#104	Gemma 4 26B A4B gemma-4-26b-a4b	Google	open	Reference only	18.2%
#105	Sarvam 105B sarvam-105b	Sarvam	open	Estimated reference	17.6%
#106	GPT-4.1 mini gpt-4-1-mini	OpenAI	closed	Estimated reference	17.5%
#107	Claude 3 Haiku claude-3-haiku	Anthropic	closed	Reference only	17.2%
#108	Nemotron 3 Nano 30B nemotron-3-nano-30b	NVIDIA	open	Estimated reference	17.1%
#109	Grok 4.1 Fast grok-4-1-fast	xAI	closed	Reference only	17%
#110	Nova Pro nova-pro	Amazon	closed	Reference only	17%
#111	K-Exaone k-exaone	LG AI Research	closed	Estimated reference	16.5%
#112	Gemma 4 12B gemma-4-12b	Google	open	Estimated reference	16%
#113	Solar Pro 2 solar-pro-2	Upstage	closed	Estimated reference	15.6%
#114	GLM-4.5-Air glm-4-5-air	Z.AI	closed	Reference only	15.5%
#115	GPT-OSS 20B gpt-oss-20b	OpenAI	open	Reference only	15.5%
#116	Ling 2.6 Flash ling-2-6-flash	InclusionAI	open	Estimated reference	15.4%
#117	MiMo-V2-Flash mimo-v2-flash	Xiaomi	open	Reference only	15.2%
#118	MiniMax M3 MiniMax-M3	MiniMax	—	Reference only	15%
#119	Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b	NVIDIA	open	Estimated reference	14.8%
#120	Llama 4 Scout llama-4-scout	Meta	open	Reference only	14.6%
#121	GPT-4.1 nano gpt-4-1-nano	OpenAI	closed	Estimated reference	13.3%
#122	Phi-4 phi-4	Microsoft	open	Reference only	13.2%
#123	Sarvam 30B sarvam-30b	Sarvam	open	Estimated reference	12.7%
#124	Gemma 3 27B gemma-3-27b	Google	open	Reference only	12.5%
#125	Exaone 4.0 32B exaone-4-0-32b	LG AI Research	open	Estimated reference	10.4%
#126	LFM2.5-8B-A1B lfm2-5-8b-a1b	LiquidAI	open	Estimated reference	9.4%
#127	Command A+ command-a-plus	Cohere	open	Estimated reference	8.9%
#128	Gemma 4 E4B gemma-4-e4b	Google	open	Estimated reference	8.6%
#129	Gemma 4 E2B gemma-4-e2b	Google	open	Estimated reference	6.7%
#130	Granite-4.0-1B granite-4-0-1b	IBM	open	Estimated reference	6.1%
#131	Granite-4.0-H-1B granite-4-0-h-1b	IBM	open	Estimated reference	5.3%
#132	LFM2.5-VL-1.6B-Extract lfm2-5-vl-1-6b-extract	LiquidAI	open	Estimated reference	5.2%
#133	Exaone 4.0 1.2B exaone-4-0-1-2b	LG AI Research	open	Estimated reference	4.7%
#134	Granite-4.0-H-350M granite-4-0-h-350m	IBM	open	Estimated reference	3.7%
#135	Granite-4.0-350M granite-4-0-350m	IBM	open	Estimated reference	3.2%

Rank

Model

Provider

License

Evidence use

Score

Claude Fable 5

claude-fable-5

Anthropic

closed

Reference only

61.4%

GPT-5.6 Sol

gpt-5.6-sol

OpenAI

closed

Reference only

58.5%

GPT-5.5

gpt-5.5

OpenAI

closed

Estimated reference

56.9%

Gemini 3 Pro

gemini-3-pro

Google

closed

Reference only

55.9%

Gemini 3.1 Pro

gemini-3-1-pro

Google

closed

Estimated reference

55.3%

Grok 4.5

grok-4.5

xAI

closed

Reference only

52.1%

Gemini 3.5 Flash

gemini-3.5-flash

Google

closed

Estimated reference

51.9%

GPT-5.3-Codex

gpt-5.3-codex

OpenAI

closed

Reference only

51.8%

Gemini 3.6 Flash

gemini-3.6-flash

Google

closed

Estimated reference

50.2%

#10

GPT-5.4

gpt-5.4

OpenAI

closed

Reference only

50%

#11

Claude Opus 4.8

claude-opus-4-8

Anthropic

closed

Reference only

46.6%

#12

Claude Opus 4.6 (Adaptive)

claude-opus-4-6-thinking

Anthropic

closed

Estimated reference

46.4%

#13

Kimi K3

kimi-k3

Moonshot AI

closed

Reference only

46%

#14

GPT-5.6 Terra

gpt-5.6-terra

OpenAI

closed

Estimated reference

45.9%

#15

Claude Opus 4.7 (Adaptive)

claude-opus-4-7-max

Anthropic

closed

Estimated reference

45.8%

#16

Claude Opus 4.5 Thinking

claude-opus-4-5-thinking

Anthropic

closed

Estimated reference

45.7%

#17

Gemini 3 Flash

gemini-3-flash

Google

closed

Reference only

45.5%

#18

Claude Opus 4.6

claude-opus-4-6

Anthropic

closed

Reference only

45.2%

#19

Muse Spark

muse-spark

Meta

closed

Reference only

44.6%

#20

GPT-5.2

gpt-5.2

OpenAI

closed

Estimated reference

43.8%

#21

Claude Opus 4.7

claude-opus-4-7

Anthropic

closed

Reference only

43.5%

#22

DeepSeek V4 Pro (Max)

deepseek-v4-pro-max

DeepSeek

open

Estimated reference

43.3%

#23

DeepSeek V4 Pro (High)

deepseek-v4-pro-high

DeepSeek

open

Estimated reference

41.8%

#24

GPT-5.6 Luna

gpt-5.6-luna

OpenAI

closed

Estimated reference

41.5%

#25

Grok 4

grok-4

xAI

closed

Reference only

41.4%

#26

Claude Opus 4.5

claude-opus-4-5

Anthropic

closed

Reference only

40.7%

#27

GPT-5 (high)

gpt-5-high

OpenAI

closed

Estimated reference

40.7%

#28

GPT-5.2 Codex

gpt-5.2-codex

OpenAI

closed

Reference only

40.7%

#29

Muse Spark 1.1

muse-spark-1-1

Meta

closed

Reference only

40.6%

#30

Inkling

inkling

Thinking Machines Lab

open

Reference only

40%

#31

GPT-5.1-Codex

gpt-5-1-codex

OpenAI

closed

Estimated reference

39.2%

#32

GPT-5.1-Codex-Max

gpt-5-1-codex-max

OpenAI

closed

Estimated reference

39.2%

#33

Gemini 2.5 Pro

gemini-2.5-pro

Google

closed

Reference only

39%

#34

GPT-5 (medium)

gpt-5-medium

OpenAI

closed

Reference only

38.9%

#35

Kimi K2.7 Code

kimi-k2.7-code

Moonshot AI

open

Estimated reference

38.6%

#36

OpenAI

closed

Reference only

38.4%

#37

Claude Sonnet 5

claude-sonnet-5

Anthropic

closed

Estimated reference

38.3%

#38

Claude Sonnet 4.6

claude-sonnet-4-6

Anthropic

closed

Reference only

38%

#39

Qwen 3.6 Max (preview)

qwen3-6-max-preview

Alibaba Cloud

closed

Reference only

37.7%

#40

GPT-5.1

gpt.5.1

OpenAI

closed

Estimated reference

37.6%

#41

GPT-5.4 mini

gpt-5.4-mini

OpenAI

closed

Estimated reference

37.5%

#42

DeepSeek V4 Flash (Max)

deepseek-v4-flash-max

DeepSeek

open

Estimated reference

37.2%

#43

Gemini 3.1 Flash-Lite

gemini-3.1-flash-lite

Google

closed

Reference only

36.4%

#44

DeepSeek V4 Flash (High)

deepseek-v4-flash-high

DeepSeek

open

Estimated reference

35.5%

#45

OpenAI

closed

Estimated reference

34.7%

#46

Grok 4.3

grok-4.3

xAI

closed

Reference only

34.6%

#47

Kimi K2.5

kimi-k2.5

Moonshot AI

—

Reference only

34.3%

#48

Kimi K2.5 (Reasoning)

kimi-k2-5-reasoning

Moonshot AI

closed

Estimated reference

34.3%

#49

Kimi K2.6

kimi-k2.6

Moonshot AI

open

Estimated reference

32.8%

#50

Hy3

hy3

Tencent

open

Estimated reference

31.5%

#51

Hy3 Preview

hy3-preview

Tencent

open

Estimated reference

31.5%

#52

Qwen3.5 397B

qwen3.5-397b-a17b

Alibaba Cloud

open

Estimated reference

31.4%

#53

Qwen3.5 397B (Reasoning)

qwen3-5-397b-reasoning

Alibaba Cloud

open

Estimated reference

31.4%

#54

DeepSeek-R1

deepseek-r1

DeepSeek

open

Reference only

31%

#55

Gemini 3.5 Flash-Lite

gemini-3.5-flash-lite

Google

closed

Estimated reference

30.3%

#56

Qwen3.7-Max

qwen3.7-max

Alibaba Cloud

—

Reference only

30.1%

#57

GLM-4.7

glm-4.7

Z.AI

open

Reference only

29.3%

#58

GLM-5V-Turbo

glm-5v-turbo

Z.AI

closed

Reference only

29.1%

#59

GLM-5-Turbo

glm-5-turbo

Z.AI

closed

Reference only

29%

#60

DeepSeek V3.1 (Reasoning)

deepseek-v3-1-reasoning

DeepSeek

open

Reference only

28.8%

#61

GLM-5

glm-5

Z.AI

open

Reference only

26.9%

#62

Kimi K2

kimi-k2

Moonshot AI

closed

Reference only

26.8%

#63

MiMo-V2-Pro

mimo-v2-pro

Xiaomi

closed

Reference only

26.8%

#64

Gemini 2.5 Flash

gemini-2.5-flash

Google

closed

Reference only

26.5%

#65

Qwen3.6 Plus

qwen3-6-plus

Alibaba Cloud

closed

Reference only

26.2%

#66

MiniMax M2.7

minimax-m2-7

MiniMax

open

Reference only

26.1%

#67

DeepSeek V3

deepseek-v3

DeepSeek

open

Reference only

25.4%

#68

GPT-5.4 nano

gpt.5.4.nano

OpenAI

closed

Reference only

25.4%

#69

Step 3.7 Flash

step-3-7-flash

StepFun

open

Estimated reference

25.4%

#70

Grok 4.1 Fast (Reasoning)

grok-4-1-fast-reasoning

xAI

closed

Reference only

25.3%

#71

GLM-5.2

glm-5-2

Z.AI

open

Estimated reference

25.1%

#72

Mistral Medium 3.5 128B

mistral-medium-3-5-128b

Mistral AI

open

Estimated reference

25.1%

#73

Qwen3.5-122B-A10B

qwen3-5-122b-a10b

Alibaba Cloud

open

Reference only

24.7%

#74

Qwen3 Max

qwen3-max

Alibaba Cloud

closed

Estimated reference

24.4%

#75

Llama 4 Maverick

llama-4-maverick

Meta

open

Reference only

24.3%

#76

DeepSeek V3.2

deepseek-v3.2

DeepSeek

open

Reference only

24.2%

#77

GLM-5.1

glm-5-1

Z.AI

open

Reference only

24.2%

#78

GPT-4.1

gpt-4-1

OpenAI

closed

Reference only

24.2%

#79

Mistral Large 3

mistral-large-2512

Mistral AI

open

Reference only

24.1%

#80

Grok Code Fast 1

grok-code-fast-1

xAI

closed

Reference only

23.8%

#81

DeepSeek V3.1

deepseek-v3-1

DeepSeek

open

Reference only

23.1%

#82

Trinity-Large-Preview

trinity-large-preview

Arcee AI

open

Estimated reference

22.8%

#83

Trinity-Large-Thinking

trinity-large-thinking

Arcee AI

open

Reference only

22.8%

#84

Grok 4 Fast (Reasoning)

grok-4-fast-reasoning

xAI

closed

Reference only

22.6%

#85

MiMo-V2.5-Pro

mimo-v2-5-pro

Xiaomi

closed

Reference only

22.6%

#86

Claude 4 Sonnet

claude-4-sonnet

Anthropic

closed

Reference only

22.4%

#87

Llama 3.1 405B

llama-3-1-405b

Meta

open

Estimated reference

22.3%

#88

Qwen3.7-Plus

qwen3.7-plus

Alibaba Cloud

—

Reference only

22.2%

#89

Mistral Small 4

mistral-small-2603

Mistral AI

open

Estimated reference

22.1%

#90

Mistral Small 4 (Reasoning)

mistral-small-4-reasoning

Mistral AI

open

Estimated reference

22.1%

#91

Nemotron 3 Ultra

nemotron-3-ultra-550b

NVIDIA

open

Estimated reference

21.6%

#92

GPT-OSS 120B

gpt-oss-120b

OpenAI

open

Reference only

21.5%

#93

Qwen3.5 27B

qwen3.5-27b

Alibaba Cloud

open

Reference only

21%

#94

GLM-4.6

glm-4.6

Z.AI

open

Reference only

20.8%

#95

Qwen3.5-35B-A3B

qwen3-5-35b-a3b

Alibaba Cloud

open

Reference only

20.5%

#96

Mistral Large 2

mistral-large-2

Mistral AI

closed

Estimated reference

20.1%

#97

Gemma 4 31B

gemma-4-31b

Google

open

Reference only

19.9%

#98

Nemotron Ultra 253B

nemotron-ultra-253b

NVIDIA

open

Estimated reference

19.9%

#99

GPT-4o

gpt-4o

OpenAI

closed

Reference only

19.7%

#100

Qwen3.6 27B

qwen3.6-27b

Alibaba Cloud

open

Estimated reference

19.2%

#101

Qwen3.6-35B-A3B

qwen3-6-35b-a3b

Alibaba Cloud

open

Estimated reference

18.9%

#102

MiMo-V2-Omni

mimo-v2-omni

Xiaomi

closed

Reference only

18.7%

#103

Mistral Medium 3

mistral-medium-3

Mistral AI

closed

Estimated reference

18.3%

#104

Gemma 4 26B A4B

gemma-4-26b-a4b

Google

open

Reference only

18.2%

#105

Sarvam 105B

sarvam-105b

Sarvam

open

Estimated reference

17.6%

#106

GPT-4.1 mini

gpt-4-1-mini

OpenAI

closed

Estimated reference

17.5%

#107

Claude 3 Haiku

claude-3-haiku

Anthropic

closed

Reference only

17.2%

#108

Nemotron 3 Nano 30B

nemotron-3-nano-30b

NVIDIA

open

Estimated reference

17.1%

#109

Grok 4.1 Fast

grok-4-1-fast

xAI

closed

Reference only

17%

#110

Nova Pro

nova-pro

Amazon

closed

Reference only

17%

#111

K-Exaone

k-exaone

LG AI Research

closed

Estimated reference

16.5%

#112

Gemma 4 12B

gemma-4-12b

Google

open

Estimated reference

16%

#113

Solar Pro 2

solar-pro-2

Upstage

closed

Estimated reference

15.6%

#114

GLM-4.5-Air

glm-4-5-air

Z.AI

closed

Reference only

15.5%

#115

GPT-OSS 20B

gpt-oss-20b

OpenAI

open

Reference only

15.5%

#116

Ling 2.6 Flash

ling-2-6-flash

InclusionAI

open

Estimated reference

15.4%

#117

MiMo-V2-Flash

mimo-v2-flash

Xiaomi

open

Reference only

15.2%

#118

MiniMax M3

MiniMax-M3

MiniMax

—

Reference only

15%

#119

Nemotron 3 Nano Omni 30B A3B

nemotron-3-nano-omni-30b-a3b

NVIDIA

open

Estimated reference

14.8%

#120

Llama 4 Scout

llama-4-scout

Meta

open

Reference only

14.6%

#121

GPT-4.1 nano

gpt-4-1-nano

OpenAI

closed

Estimated reference

13.3%

#122

Phi-4

phi-4

Microsoft

open

Reference only

13.2%

#123

Sarvam 30B

sarvam-30b

Sarvam

open

Estimated reference

12.7%

#124

Gemma 3 27B

gemma-3-27b

Google

open

Reference only

12.5%

#125

Exaone 4.0 32B

exaone-4-0-32b

LG AI Research

open

Estimated reference

10.4%

#126

LFM2.5-8B-A1B

lfm2-5-8b-a1b

LiquidAI

open

Estimated reference

9.4%

#127

Command A+

command-a-plus

Cohere

open

Estimated reference

8.9%

#128

Gemma 4 E4B

gemma-4-e4b

Google

open

Estimated reference

8.6%

#129

Gemma 4 E2B

gemma-4-e2b

Google

open

Estimated reference

6.7%

#130

Granite-4.0-1B

granite-4-0-1b

IBM

open

Estimated reference

6.1%

#131

Granite-4.0-H-1B

granite-4-0-h-1b

IBM

open

Estimated reference

5.3%

#132

LFM2.5-VL-1.6B-Extract

lfm2-5-vl-1-6b-extract

LiquidAI

open

Estimated reference

5.2%

#133

Exaone 4.0 1.2B

exaone-4-0-1-2b

LG AI Research

open

Estimated reference

4.7%

#134

Granite-4.0-H-350M

granite-4-0-h-350m

IBM

open

Estimated reference

3.7%

#135

Granite-4.0-350M

granite-4-0-350m

IBM

open

Estimated reference

3.2%

Definition and scoring

Organisation

Artificial Analysis

What does Artificial Analysis Omniscience Accuracy measure?

A display-only Artificial Analysis knowledge metric for the proportion of correctly answered questions.

Which model scores highest on Artificial Analysis Omniscience Accuracy?

Claude Fable 5 by Anthropic currently leads with 61.4%.

How many models are evaluated on Artificial Analysis Omniscience Accuracy?

135 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 Omniscience Accuracy

Leaderboard · 135 models

Claude Fable 5

GPT-5.6 Sol

GPT-5.5

See the field.