What does Artificial Analysis · Quality Index measure?

Artificial Analysis · Quality Index is a knowledge benchmark in the BenchGecko catalog. 96 AI models have been tested on it. Scores range from 2.4 to 59.9 out of 60.

Which model leads on Artificial Analysis · Quality Index?

Claude Fable 5 from Anthropic leads Artificial Analysis · Quality Index with a score of 59.9. The median score across 96 tested models is 30.2.

Is Artificial Analysis · Quality Index saturated?

Yes · the top model on Artificial Analysis · Quality Index has reached 59.9 out of 60, within 5% of the theoretical ceiling. This benchmark is approaching saturation and may be replaced by a harder successor.

Does Artificial Analysis · Quality Index predict performance on other benchmarks?

Yes · Artificial Analysis · Quality Index scores correlate 0.97 with MATH level 5 across 6 shared models. Models that do well on Artificial Analysis · Quality Index tend to do well on MATH level 5.

How often is Artificial Analysis · Quality Index data refreshed?

BenchGecko pulls updates daily. New model scores on Artificial Analysis · Quality Index appear as soon as they are published by Epoch AI or the model provider.

Benchmark · KnowledgeSettled

Artificial Analysis · Quality Index

Name: Artificial Analysis · Quality Index Benchmark
Creator: BenchGecko
License: https://creativecommons.org/licenses/by/4.0/

Updated 2026-06-17

Models tested

Top score

59.9

Claude Fable 5

Median

30.2

min 2.4

Top-5 spread

σ 2.5

Competitive

The Frontier

Best score over time · one chart, every benchmark

Chart type

Frontier on Artificial Analysis · Quality Index rose from 4.9 to 59.9 in 17 months · +55.0 points · latest leader Claude Fable 5 from Anthropic.

Pink dots = frontier records · 11 totalClick to open model page

Full rankings

96 models tested · sorted by score

#	Model	Score	Price
1	Claude Fable 5· Anthropic	59.9	$10.00
2	GPT-5.4· OpenAI	57.2	$2.50
3	Claude Opus 4.8 (Fast)· Anthropic	55.7	$10.00
4	Claude Opus 4.7 (Fast)· Anthropic	53.5	$30.00
5	Claude Opus 4.6 (Fast)· Anthropic	53.0	$30.00
6	GLM 5.2· z-ai	51.1	$1.00
7	Gemini 3.5 Flash· Google DeepMind	50.2	$1.50
8	MiMo-V2-Pro· xiaomi	49.2	$1.00
9	Claude Sonnet 4.6· Anthropic	47.2	$3.00
10	Kimi K2.5· moonshotai	46.8	$0.38
11	Gemini 3.1 Pro Preview· Google DeepMind	46.5	$2.00
12	Gemini 3 Flash Preview· Google DeepMind	46.4	$0.50
13	Qwen3.7 Max· Alibaba Qwen	46.0	$1.25
14	MiniMax M3· minimax	44.4	$0.30
15	DeepSeek V4 Pro· DeepSeek	44.3	$0.43
16	GPT-5.3-Codex· OpenAI	44.3	$1.75
17	MiMo-V2-Omni· xiaomi	43.4	$0.40
18	U Muse Spark· Unknown	43.1	—
19	GLM 5V Turbo· z-ai	42.9	$1.20
20	Kimi K2.6· moonshotai	42.8	$0.66
21	MiMo-V2.5-Pro· xiaomi	42.2	$0.43
22	Qwen3.5-27B· Alibaba Qwen	42.1	$0.20
23	Kimi K2.7 Code· moonshotai	42.0	$0.61
24	DeepSeek V3.2· DeepSeek	41.7	$0.21
25	MiMo-V2-Flash· xiaomi	41.5	$0.09
26	Gemini 3 Pro· Google DeepMind	41.3	—
27	DeepSeek V4 Flash· DeepSeek	40.3	$0.08
28	GLM 5.1· z-ai	40.2	$0.97
29	MiMo-V2.5· xiaomi	40.1	$0.10
30	GPT-5.4 Mini· OpenAI	40.0	$0.75
31	Qwen3 Max Thinking· Alibaba Qwen	39.9	$0.78
32	Qwen3.6 Plus· Alibaba Qwen	39.6	$0.33
33	Qwen3.7 Plus· Alibaba Qwen	39.0	$0.32
34	Grok 4.1 Fast· xAI	38.6	$0.20
35	GPT-5.4 Nano· OpenAI	38.2	$0.20
36	MiniMax M2.7· minimax	38.1	$0.24
37	GLM 5 Turbo· z-ai	38.1	$1.20
38	Step 3.5 Flash· stepfun	37.8	$0.10
39	Nemotron 3 Ultra· NVIDIA	37.8	$0.50
40	Grok 4.3· xAI	37.6	$1.25
41	Qwen3.6 27B· Alibaba Qwen	37.0	$0.28
42	Qwen3.5 397B A17B· Alibaba Qwen	33.7	$0.39
43	Hy3 preview· tencent	33.6	$0.06
44	Gemini 3.1 Flash Lite Preview· Google DeepMind	33.5	$0.25
45	Qwen3.5-122B-A10B· Alibaba Qwen	32.3	$0.26
46	Qwen3.6 35B A3B· Alibaba Qwen	31.6	$0.14
47	I Ring-2.6-1T· inclusionai	30.6	$0.07
48	o3· OpenAI	30.4	$2.00
49	Mistral Medium 3.5· Mistral AI	29.9	$1.50
50	Step 3.7 Flash· stepfun	29.7	$0.20
51	DeepSeek V3.2 Speciale· DeepSeek	29.4	$0.40
52	Gemma 4 31B (free)· Google DeepMind	29.4	$0.00
53	Command A· Cohere	29.3	$2.50
54	Grok Code Fast 1· xAI	28.7	$0.20
55	R1 0528· DeepSeek	27.1	$0.50
56	Gemini 2.5 Pro· Google DeepMind	27.0	$1.25
57	I Ling-2.6-1T· inclusionai	26.1	$0.07
58	Gemma 4 26B A4B (free)· Google DeepMind	25.7	$0.00
59	Mercury 2· inception	25.3	$0.25
60	Gemini 3.1 Flash Lite· Google DeepMind	25.0	$0.25
61	Qwen3.5-9B· Alibaba Qwen	25.0	$0.10
62	Qwen3 Coder 480B A35B (free)· Alibaba Qwen	24.8	$0.00
63	Trinity Large Thinking· arcee-ai	24.5	$0.25
64	gpt-oss-120b (free)· OpenAI	23.8	$0.00
65	Qwen3.5-35B-A3B· Alibaba Qwen	23.4	$0.14
66	Gemini 2.5 Flash Lite· Google DeepMind	21.6	$0.10
67	Mistral Medium 3.1· Mistral AI	21.3	$0.40
68	Qwen3 Coder Next· Alibaba Qwen	21.2	$0.11
69	Mistral Small 4· Mistral AI	20.8	$0.15
70	North Mini Code (free)· Cohere	20.6	$0.00
71	Qwen3.5 4B· Alibaba	20.1	—
72	Qwen3 Next 80B A3B Instruct (free)· Alibaba Qwen	19.8	$0.00
73	I Ling-2.6-flash· inclusionai	19.3	$0.01
74	R1 Distill Llama 70B· DeepSeek	15.9	$0.80
75	INTELLECT-3· prime-intellect	15.6	$0.20
76	Llama 3.1 Nemotron Ultra 253B v1· NVIDIA	15.0	$0.60
77	ERNIE 4.5 300B A47B · baidu	15.0	$0.28
78	gpt-oss-20b (free)· OpenAI	14.9	$0.00
79	Llama 4 Maverick· Meta	14.3	$0.15
80	Solar Pro 3· upstage	14.1	$0.15
81	Qwen3 Next 80B A3B Instruct· Alibaba Qwen	13.7	$0.09
82	Qwen3.5 2B· Alibaba	10.2	—
83	N Nanbeige4.1 3B· Nanbeige	10.1	—
84	Llama 4 Scout· Meta	10.0	$0.10
85	Granite 4.1 8B· ibm-granite	8.9	$0.05
86	NVIDIA Nemotron Nano 9B V2· NVIDIA	8.8	—
87	Phi 4 Mini Instruct· Microsoft	8.4	—
88	Qwen3.5 0.8B· Alibaba	5.0	—
89	LFM2-24B-A2B· liquid	5.0	$0.03
90	Phi 4· Microsoft	4.9	$0.07
91	Phi 4 Multimodal Instruct· Microsoft	4.5	—
92	Reka Flash 3· rekaai	4.1	$0.10
93	Phi 4 Mini Instruct· Microsoft	3.0	$0.08
94	LFM2.5-1.2B-Thinking (free)· liquid	2.8	$0.00
95	LFM2.5-1.2B-Instruct (free)· liquid	2.7	$0.00
96	Granite 4.0 Micro· ibm-granite	2.4	$0.02