Knowledge benchmark

AA-HLE leaderboard

Artificial Analysis Humanity's Last Exam. Every model the catalog carries a published AA-HLE value for, ranked by that value.

CategoryKnowledge

MeasureAccuracy

TasksExpert-level questions

DifficultyFrontier expert reasoning

Published byArtificial Analysis Humanity's Last Exam Benchmark Leaderboard

A display-only Artificial Analysis Humanity's Last Exam score.

AA-HLE ranking

181 models with a published AA-HLE value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

Models ranked by their published Artificial Analysis Humanity's Last Exam value
Rank	Model	Provider	Accuracy
1	Claude Fable 5.1	Anthropic	59.1
2	Claude Fable 5	Anthropic	55.5
3	Claude Opus 5	Anthropic	54.9
4	GPT-6 Astra	OpenAI	54.7
5	GPT-5.6 Sol	OpenAI	49.5
6	Claude Opus 4.8	Anthropic	48.7
6	Muse Spark 1.3	Meta	48.7
8	Gemini 3.7 Flash	Google	47.9
9	Gemini 3.8 Flash	Google	47.8
10	Gemini 3.1 Pro	Google	47.0
11	Kimi K3	Moonshot AI	46.9
12	Muse Spark 1.1	Meta	46.2
13	GPT-5.5	OpenAI	45.8
14	Muse Spark 1.2	Meta	45.5
15	GPT-5.4	OpenAI	43.7
16	Qwen3.8 Max Preview	Alibaba	43.1
17	GPT-5.6 Terra	OpenAI	42.9
17	Grok 4.6	xAI	42.9
19	Gemini 3.5 Flash	Google	42.7
19	Grok 4.5	xAI	42.7
21	GPT-5.3 Codex	OpenAI	42.5
22	Claude Opus 4.7 (Adaptive)	Anthropic	42.3
22	GLM-5.3	Z.AI	42.3
24	Claude Sonnet 5	Anthropic	41.3
25	GLM-5.2	Z.AI	41.1
26	DeepSeek V4 Pro 0813	DeepSeek	41.0
27	Gemini 3.6 Flash	Google	40.8
28	Muse Spark	Meta	40.7
29	Qwen3.7 Max	Alibaba	40.5
30	Claude Opus 4.6 (Adaptive)	Anthropic	39.9
30	GLM-5.3-Flash	Z.AI	39.9
32	Gemini 3 Pro	Google	39.7
33	GPT-5.6 Luna	OpenAI	39.5
34	DeepSeek V4.1 Flash	DeepSeek	39.2
35	MiniMax M3	MiniMax	39.0
36	DeepSeek V4 Flash 0731	DeepSeek	38.6
37	Qwen3.8-Flash-Next	Alibaba	38.0
38	GPT-5.2	OpenAI	37.7
39	Kimi K2.6	Moonshot AI	37.5
40	Grok 4.3	xAI	37.2
41	GPT-5.2-Codex	OpenAI	35.7
41	MiMo-V2.5-Pro	Xiaomi	35.7
43	Qwen3.7 Plus	Alibaba	35.6
44	Kimi K2.7 Code	Moonshot AI	35.0
45	APApodex 1.1	Apodex	34.1
45	APApodex 1.1 Mini	Apodex	34.1
47	Qwen3.8-27B	Alibaba	33.9
48	Hy3	Tencent	33.5
48	Hy3 Preview	Tencent	33.5
50	Claude Opus 4.7	Anthropic	33.3
50	TMInkling-Small	Thinking Machines Lab	33.3
52	TMInkling	Thinking Machines Lab	31.9
53	Qwen 3.6 Max (preview)	Alibaba	30.8
54	Kimi K2.5	Moonshot AI	30.7
54	Kimi K2.5 (Reasoning)	Moonshot AI	30.7
56	MiMo-V2-Pro	Xiaomi	30.4
57	Claude Opus 4.5 Thinking	Anthropic	30.1
57	GLM-5.1	Z.AI	30.1
59	STA.X K2	SK Telecom	29.6
59	MiniMax M2.7	MiniMax	29.6
61	GLM-5	Z.AI	29.3
62	Solar Pro 4	Upstage	29.2
63	GPT-5 (high)	OpenAI	28.5
63	GPT-5.1	OpenAI	28.5
65	Nemotron 3 Ultra	NVIDIA	28.4
66	GPT-5.4 nano	OpenAI	28.3
67	GPT-5.4 mini	OpenAI	28.1
68	GLM-5-Turbo	Z.AI	27.8
68	Qwen3.6 Plus	Alibaba	27.8
70	GLM-4.7	Z.AI	27.4
71	Grok 4	xAI	26.7
72	GPT-5.1-Codex	OpenAI	25.7
72	GPT-5.1-Codex-Max	OpenAI	25.7
74	GPT-5 (medium)	OpenAI	25.4
75	Qwen3.5-122B-A10B	Alibaba	25.2
76	Qwen3.5-27B	Alibaba	23.9
77	Ling 3.0 Flash	InclusionAI	23.7
77	Ling 3.0 Flash FP8	InclusionAI	23.7
79	Gemma 4 31B	Google	23.6
80	Qwen3.6-27B	Alibaba	23.1
81	Gemini 2.5 Pro	Google	22.5
82	Qwen3.6-35B-A3B	Alibaba	22.2
83	MiMo-V2-Omni	Xiaomi	22.1
84	Ling 3.0 Flash VL	InclusionAI	22.0
84	Muse Glimmer 30B	Meta	22.0
86	Step 3.7 Flash	StepFun	21.4
87	Qwen3.5-35B-A3B	Alibaba	21.0
88	Nemotron 3 Super 100B	NVIDIA	20.8
89	o3	OpenAI	20.1
90	Qwen3.5 397B	Alibaba	19.8
90	Qwen3.5 397B (Reasoning)	Alibaba	19.8
92	GPT-OSS 120B	OpenAI	19.6
93	Gemma 4 26B A4B	Google	19.3
93	Grok 4.1 Fast (Reasoning)	xAI	19.3
95	Claude Opus 4.6	Anthropic	19.1
95	Grok 4 Fast (Reasoning)	xAI	19.1
97	Gemini 3.5 Flash-Lite	Google	18.8
98	MCQuasar 438B	Multiverse Computing	18.7
99	K-EXAONE 2.0	LG AI Research	18.6
100	GLM-5V-Turbo	Z.AI	17.1
101	DeepSeek-R1	DeepSeek	15.8
101	Trinity-Large-Preview	Arcee AI	15.8
101	Trinity-Large-Thinking	Arcee AI	15.8
104	Gemma 4 12B	Google	15.7
105	Gemini 3 Flash	Google	15.0
106	DeepSeek V3.1 (Reasoning)	DeepSeek	14.3
107	K-Exaone	LG AI Research	13.9
108	Mistral Medium 3.5 128B	Mistral	13.8
109	Claude Sonnet 4.6	Anthropic	13.3
110	Claude Opus 4.5	Anthropic	13.2
111	Claude 4.1 Opus Thinking	Anthropic	12.5
112	Command A+	Cohere	12.0
113	Qwen3 Max	Alibaba	11.9
114	Nemotron 3 Nano 30B	NVIDIA	11.4
115	DeepSeek V3.2	DeepSeek	11.2
115	Granite 4.2 30B	IBM	11.2
117	North Mini Code	Cohere	11.1
118	GPT-OSS 20B	OpenAI	11.0
118	SASarvam 105B	Sarvam	11.0
120	Nemotron 3.5 Lightning 30B A3B NVFP4	NVIDIA	10.6
121	Solar Pro 3	Upstage	10.3
122	Mistral Small 4	Mistral	9.9
122	Mistral Small 4 (Reasoning)	Mistral	9.9
124	Granite 4.2 8B	IBM	9.7
125	Ling 3.0 Tiny	InclusionAI	9.3
126	OPMiniCPM5-2B	OpenBMB	8.9
127	MiMo-V2-Flash	Xiaomi	8.6
128	Grok Code Fast 1	xAI	8.0
129	o3-mini	OpenAI	7.9
130	Qwen3-Omni-30B-A3B-Thinking	Alibaba	7.5
130	SASarvam 30B	Sarvam	7.5
132	Kimi K2	Moonshot AI	7.4
132	Nemotron Ultra 253B	NVIDIA	7.4
134	GLM-4.5-Air	Z.AI	7.0
134	o1	OpenAI	7.0
136	LFM2.5-8B-A1B	LiquidAI	6.9
137	CECeleris-1	Celeris	6.8
138	DeepSeek V3.1	DeepSeek	6.7
139	Granite 4.2 3B	IBM	6.6
140	Granite-4.0-H-350M	IBM	6.4
141	Ling 2.6 Flash	InclusionAI	6.3
142	LFM2.5-2.6B	LiquidAI	6.2
143	Exaone 4.0 1.2B	LG AI Research	5.7
144	GLM-4.6	Z.AI	5.5
144	Granite-4.0-350M	IBM	5.5
146	Grok 4.1 Fast	xAI	5.1
146	LFM2.5-VL-1.6B-Extract	LiquidAI	5.1
148	Exaone 4.0 32B	LG AI Research	5.0
148	GPT-4.1 mini	OpenAI	5.0
148	Granite-4.0-H-1B	IBM	5.0
148	Phi-4 Multimodal Instruct	Microsoft	5.0
152	Llama 4 Maverick	Meta	4.9
153	Gemma 4 E2B	Google	4.8
153	Granite-4.0-1B	IBM	4.8
153	Nemotron 3 Nano Omni 30B A3B	NVIDIA	4.8
156	Gemini 2.5 Flash	Google	4.7
157	DeepSeek R1 Distill Qwen 32B	DeepSeek	4.6
157	Gemini 1.5 Pro	Google	4.6
157	Qwen3-Omni-30B-A3B-Instruct	Alibaba	4.6
160	Gemma 3 27B	Google	4.4
161	Claude 4 Sonnet	Anthropic	4.3
162	Gemini 1.0 Pro	Google	4.2
162	GPT-4.1	OpenAI	4.2
162	GPT-4o mini	OpenAI	4.2
162	Mistral Large 3	Mistral	4.2
166	Claude 3 Haiku	Anthropic	4.1
166	Mistral Medium 3	Mistral	4.1
168	Llama 3.1 405B	Meta	4.0
169	Gemma 4 E4B	Google	3.8
169	GPT-4.1 nano	OpenAI	3.8
169	Llama 4 Scout	Meta	3.8
169	Phi-4	Microsoft	3.8
173	Solar Pro 2	Upstage	3.7
174	FAUltravox v0.6 Llama 3.3 70B	Fixie AI	3.6
175	Qwen2.5 Coder 32B Instruct	Alibaba	3.5
176	Mistral Large 2	Mistral	3.3
177	Nova Pro	Amazon	3.2
178	GPT-4 Turbo	OpenAI	3.1
179	DeepSeek V3	DeepSeek	2.9
180	Claude 3 Opus	Anthropic	2.8
181	GPT-4o	OpenAI	2.4

Evidence key: ObservedLast good

Rows are ordered by the value Artificial Analysis Humanity's Last Exam Benchmark Leaderboard 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.

All leaderboards · Knowledge capability leaderboard

Explore models

Top Models

Featured

Capabilities

Benchmarks

Articles

AA-HLE leaderboard

AA-HLE ranking