GDPval-AA leaderboard

A display-only Artificial Analysis normalized score for economically valuable tasks.

Models ranked by their published GDPval-AA normalized value

Rank	Model	Provider	Normalized score
1	Claude Opus 5	Anthropic	61.8
2	Claude Fable 5.1	Anthropic	61.2
3	Muse Spark 1.3	Meta	60.2
4	Qwen3.8 Max Preview	Alibaba	58.2
5	Qwen3.8-Flash-Next	Alibaba	57.4
6	Grok 4.6	xAI	57.1
7	GLM-5.3	Z.AI	56.7
8	Claude Fable 5	Anthropic	56.6
8	DeepSeek V4.1 Flash	DeepSeek	56.6
10	DeepSeek V4 Pro 0813	DeepSeek	54.5
11	GPT-5.6 Sol	OpenAI	54.3
12	GPT-6 Astra	OpenAI	54.0
13	Kimi K3	Moonshot AI	52.4
14	Muse Spark 1.2	Meta	51.2
15	Claude Sonnet 5	Anthropic	50.0
16	Claude Opus 4.8	Anthropic	49.5
17	GPT-5.6 Terra	OpenAI	48.8
18	Gemini 3.8 Flash	Google	48.2
18	Qwen3.8-27B	Alibaba	48.2
20	GPT-5.6 Luna	OpenAI	47.8
21	DeepSeek V4 Flash 0731	DeepSeek	47.1
22	Gemini 3.7 Flash	Google	46.7
23	Grok 4.5	xAI	46.5
24	GLM-5.2	Z.AI	45.3
25	Claude Opus 4.7 (Adaptive)	Anthropic	44.8
25	GPT-5.5	OpenAI	44.8
27	Gemini 3.5 Flash	Google	42.2
28	Gemini 3.6 Flash	Google	41.6
29	GPT-5.4	OpenAI	40.3
30	MiniMax M3	MiniMax	40.2
31	Muse Spark 1.1	Meta	39.7
32	APApodex 1.1	Apodex	38.7
32	APApodex 1.1 Mini	Apodex	38.7
34	MCQuasar 438B	Multiverse Computing	37.0
35	Ling 3.0 Flash VL	InclusionAI	36.2
36	Hy3 Preview	Tencent	35.8
37	TMInkling-Small	Thinking Machines Lab	34.6
38	Qwen3.7 Max	Alibaba	34.5
39	MiMo-V2.5-Pro	Xiaomi	34.3
40	GLM-5.1	Z.AI	34.0
41	Solar Pro 4	Upstage	33.6
42	TMInkling	Thinking Machines Lab	33.3
43	Nemotron 3 Ultra	NVIDIA	33.1
44	Hy3	Tencent	31.8
45	Kimi K2.7 Code	Moonshot AI	30.7
46	GLM-4.7	Z.AI	29.8
46	Kimi K2.6	Moonshot AI	29.8
48	GPT-5.4 mini	OpenAI	29.7
49	MiniMax M2.7	MiniMax	29.4
50	Grok 4.3	xAI	29.2
51	Muse Spark	Meta	28.8
52	Qwen3.6-27B	Alibaba	28.4
53	Qwen3.6 Plus	Alibaba	28.3
54	Gemini 3.5 Flash-Lite	Google	28.2
55	STA.X K2	SK Telecom	27.2
56	GPT-5.4 nano	OpenAI	26.8
57	Ling 3.0 Flash	InclusionAI	25.9
57	Ling 3.0 Flash FP8	InclusionAI	25.9
59	Step 3.7 Flash	StepFun	25.8
60	GPT-5 (high)	OpenAI	25.7
61	Qwen3.6-35B-A3B	Alibaba	24.5
62	Kimi K2.5	Moonshot AI	21.8
62	Kimi K2.5 (Reasoning)	Moonshot AI	21.8
64	GPT-5.1	OpenAI	21.5
65	Qwen3.5-122B-A10B	Alibaba	21.3
66	K-EXAONE 2.0	LG AI Research	20.9
67	Gemini 3.1 Pro	Google	20.2
68	Muse Glimmer 30B	Meta	19.6
69	Qwen3.7 Plus	Alibaba	19.3
70	Mistral Medium 3.5 128B	Mistral	18.8
71	OPMiniCPM5-2B	OpenBMB	16.4
72	MiMo-V2-Flash	Xiaomi	14.4
73	Nemotron 3.5 Lightning 30B A3B NVFP4	NVIDIA	13.3
74	Gemma 4 31B	Google	12.8
75	GPT-OSS 120B	OpenAI	12.2
76	Granite 4.2 30B	IBM	11.1
77	Ling 3.0 Tiny	InclusionAI	10.8
78	Gemma 4 26B A4B	Google	9.7
79	Command A+	Cohere	7.9
80	Granite 4.2 8B	IBM	7.3
81	Nemotron 3 Super 100B	NVIDIA	7.2
82	Gemini 2.5 Pro	Google	5.8
83	Gemma 4 12B	Google	4.5
84	Mistral Large 3	Mistral	4.4
85	K-Exaone	LG AI Research	2.0
86	Mistral Small 4	Mistral	1.8
86	Mistral Small 4 (Reasoning)	Mistral	1.8
88	GPT-OSS 20B	OpenAI	0.7
89	Trinity-Large-Preview	Arcee AI	0.6
89	Trinity-Large-Thinking	Arcee AI	0.6
91	CECeleris-1	Celeris	0.0
91	DeepSeek V3	DeepSeek	0.0
91	Gemma 3 27B	Google	0.0
91	Gemma 4 E2B	Google	0.0
91	Gemma 4 E4B	Google	0.0
91	GPT-4.1 mini	OpenAI	0.0
91	GPT-4.1 nano	OpenAI	0.0
91	GPT-4o mini	OpenAI	0.0
91	Granite 4.2 3B	IBM	0.0
91	LFM2.5-2.6B	LiquidAI	0.0
91	Ling 2.6 Flash	InclusionAI	0.0
91	Llama 4 Maverick	Meta	0.0
91	Llama 4 Scout	Meta	0.0
91	Nemotron 3 Nano 30B	NVIDIA	0.0
91	Nemotron 3 Nano Omni 30B A3B	NVIDIA	0.0
91	North Mini Code	Cohere	0.0
91	Solar Pro 3	Upstage	0.0
91	FAUltravox v0.6 Llama 3.3 70B	Fixie AI	0.0

Evidence key: Observed

Rows are ordered by the value Artificial Analysis model benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.