Explore and compare LLMs

Q: How do I compare LLMs?

Sort by Quality Index to find the strongest models overall, then filter by price, speed, or context window to match your constraints. Use the Compare page to put 2–4 finalists head to head.

Find the models that fit your workload by capability, task economics, speed, context, and provider availability.

Artificial Analysis · snapshot synced Jul 28, 2026, 14:54 UTCAA data · Jul 28, 14:54 UTC173 models · 79 providersLatest tracked Jul 30, 2026 · Index v4.1

Rank by

Show

Model rankings

155 results · sorted by intelligence

Open a row for metrics and endpoints

#
1	Claude Opus 5Anthropic	60.7	78	55.3	$0.426	13s	1.0M	3
2	Claude Fable 5Anthropic	59.9	76.5	52.8	$2.75	1.6 min	1.0M	3
3	GPT-5.6 SolOpenAI	58.9	77.4	54	$0.320	11s	1.0M	2
4	GPT-5.6 Sol (xhigh)OpenAI	57.7	78.3	51.8	$0.944	53s	1.0M	1
5	Kimi K3OpenKimi	57.1	76.2	50.1	$0.723	76s	1.0M	9
6	GPT-5.6 Sol (high)OpenAI	55.9	77.2	48.5	$0.771	22s	1.0M	1
7	Claude Opus 4.8Anthropic	55.7	74.3	47.2	$2.03	19s	1.0M	3
8	GPT-5.6 TerraOpenAI	55	76.7	47.4	$0.151	5.5s	1.0M	2
9	Grok 4.5 (high)SpaceXAI	53.8	72.4	45.7	$0.441	17s	500K	1
10	GPT-5.6 Sol (medium)OpenAI	53.6	76.3	44.5	$0.514	14s	1.0M	1
11	Claude Sonnet 5Anthropic	53.4	71.5	46.7	$0.374	9.1s	1.0M	5
12	GPT-5.6 Terra (xhigh)OpenAI	51.6	70.6	44.7	$0.430	17s	1.0M	1
13	GPT-5.6 LunaOpenAI	51.2	71.4	45.6	$0.017	3.6s	1.0M	2
14	GLM-5.2OpenZ AI	51.1	68.8	43.1	$0.267	10s	1.0M	14
15	Muse Spark 1.1 (xhigh)OpenMeta	50.6	71.3	37.5	$0.261	22s	1.0M	1
16	Gemini 3.5 Flash (high)Google	50.2	70.1	37.4	$0.691	24s	1.0M	1
17	Gemini 3.6 Flash (high)Google	50.1	69.2	38.7	$0.557	17s	1.0M	1
18	GPT-5.6 Sol (low)OpenAI	49.4	69.7	40	$0.307	12s	1.0M	1
19	GPT-5.6 Luna (xhigh)OpenAI	49.1	68.6	42.9	$0.043	43s	1.0M	1
20	GPT-5.6 Terra (high)OpenAI	49	67.1	41.3	$0.304	6.9s	1.0M	1
21	Kimi K3 (low)OpenKimi	46.6	72	37	$0.243	81s	1.0M	1
22	Gemini 3.1 Pro PreviewGoogle	46.5	68.8	21.4	$0.291	28s	1.0M	2
23	GPT-5.6 Luna (high)OpenAI	46.1	63.3	40.1	$0.025	12s	1.0M	1
24	Qwen3.7 MaxOpenAlibaba	46	66	30.6	$1.28	17s	1.0M	2
25	GPT-5.6 Terra (medium)OpenAI	45.6	64.7	37	$0.160	6.7s	1.0M	1
26	Gemini 3.5 Flash (medium)Google	45.4	N/A	N/A	N/A	20s	1.0M	1
27	MiniMax-M3OpenMiniMax	44.4	58.6	35.4	$0.137	40s	1.0M	8
28	GPT-5.3 Codex (xhigh)OpenAI	44.3	N/A	N/A	N/A	74s	400K	1
29	DeepSeek V4 ProOpenDeepSeek	44.3	59.4	36.4	$0.043	9.5s	1.0M	8
30	Claude Opus 4.7Anthropic	42.7	N/A	N/A	N/A	13s	1.0M	2
31	MiMo-V2.5-ProOpenXiaomi	42.2	60.2	29.1	$0.047	13s	1.0M	3
32	Kimi K2.7 CodeOpenKimi	41.9	60.8	29.6	$0.221	58s	262K	10
33	Hy3OpenTencent	41.2	58.8	30.7	$0.033	40s	262K	4
34	Nex-N2-ProOpenNex AGI	41	59.1	31	N/A	21s	262K	1
35	Inkling (xhigh)OpenThinking Machines	40.7	52.1	32.3	N/A	31s	524K	3
36	GPT-5.6 Terra (low)OpenAI	40.5	58.1	30.6	$0.116	6.4s	1.0M	1
37	DeepSeek V4 FlashOpenDeepSeek	40.3	56.2	31.1	$0.022	5.7s	1.0M	7
38	Inkling SmallOpenThinking Machines	40.2	52.9	30.8	$0.073	29s	262K	1
39	Qwen3.6 PlusOpenAlibaba	39.6	54.5	27.6	$0.314	1.9 min	1.0M	1
40	Qwen3.7 PlusOpenAlibaba	39	55.9	20.8	$0.226	50s	1.0M	1
41	Agnes 2.5 Pro AlphaSapiens AI	38.8	58.8	25.2	N/A	24s	1.0M	1
42	GPT-5.6 Luna (medium)OpenAI	38.1	50.7	31	$0.015	5.2s	1.0M	1
43	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	49.3	27.4	$0.413	16s	512K	6
44	MiMo-V2.5OpenXiaomi	37.2	56.8	23.7	$0.010	31s	1.0M	4
45	Qwen3.6 27B (Reasoning)OpenAlibaba	37.1	53.7	27	$0.293	2.0 min	262K	5
46	Gemini 3.5 Flash-LiteGoogle	36.5	49.3	26.8	$0.096	9.3s	1.0M	1
47	Grok 4.3 (medium)SpaceXAI	36	N/A	N/A	N/A	13s	1.0M	3
48	Grok 4.3 (low)SpaceXAI	35.4	N/A	N/A	N/A	8.8s	1.0M	3
49	Gemini 3.5 FlashGoogle	34.9	N/A	N/A	N/A	4.3s	1.0M	1
50	Kimi K2.6OpenKimi	34.6	N/A	N/A	N/A	16s	262K	10
51	Claude Sonnet 4.6Anthropic	34.3	N/A	N/A	N/A	13s	1.0M	1
52	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	33.7	48.2	19.8	$0.359	56s	262K	8
53	KAT Coder Pro V2KwaiKAT	33.7	59.5	15.5	N/A	6.4s	256K	1
54	Hy3-preview (Reasoning)OpenTencent	33.6	N/A	N/A	N/A	19s	256K	1
55	LongCat 2.0OpenLongCat	33.5	45.3	21.8	$0.122	62s	1.0M	1
56	GPT-5.6 Luna (low)OpenAI	33.3	44.2	25.4	$0.013	4.6s	1.0M	1
57	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	32.3	45.7	20.7	$0.257	21s	262K	4
58	Qwen3.5 397B A17BOpenAlibaba	32	N/A	N/A	N/A	9.8s	262K	6
59	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	31.6	41.9	21.4	$0.194	44s	262K	6
60	Qwen3.5 Omni PlusOpenAlibaba	30.6	N/A	N/A	N/A	12s	256K	1
61	Ring-2.6-1TOpenInclusionAI	30.6	42.8	18.9	$0.345	24s	262K	1
62	Qwen3.6 27BOpenAlibaba	30.5	46.6	23.3	$0.396	13s	262K	4
63	o3OpenAI	30.4	N/A	N/A	N/A	10s	200K	2
64	Step 3.7 FlashOpenStepFun	30.3	39.6	21.5	$0.091	7.3s	256K	2
65	Mistral Medium 3.5OpenMistral	29.9	46.9	19	$0.557	40s	262K	1
66	Claude 4.5 Haiku (Reasoning)Anthropic	29.6	43.9	16.4	$0.249	21s	200K	4
67	Gemma 4 31B (Reasoning)OpenGoogle	29.4	43.4	14.4	$0.0000	65s	262K	12
68	Qwen3.5 122B A10BOpenAlibaba	27.6	43.3	15.8	$0.192	5.8s	262K	2
69	Hy3-previewOpenTencent	26.1	N/A	N/A	N/A	6.0s	328K	1
70	Step 3.5 Flash 2603StepFun	26	N/A	N/A	N/A	11s	256K	1
71	Gemini 2.5 ProGoogle	25.8	33.3	7.1	$0.215	26s	1.0M	2
72	Gemma 4 26B A4B (Reasoning)OpenGoogle	25.7	39.3	11	$0.044	N/A	1.0M	6
73	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	37.7	8.7	$0.231	17s	262K	2
74	Gemini 3.1 Flash-LiteGoogle	25	34.7	6.2	$0.043	7.6s	1.0M	1
75	Grok 4.3SpaceXAI	24.8	35.2	22.8	$0.294	4.9s	1.0M	2
76	Qwen3.6 35B A3BOpenAlibaba	24.2	28.1	19.1	$0.630	5.2s	262K	5
77	Qwen3.5 35B A3BOpenAlibaba	24	37	11.8	$0.231	5.0s	262K	2
78	gpt-oss-120b (high)OpenOpenAI	23.8	30.4	13.2	$0.061	14s	131K	16
79	Claude 4.5 HaikuAnthropic	23.7	N/A	N/A	N/A	6.7s	200K	4
80	Command A+OpenCohere	22.5	27.8	9.2	$0.0000	13s	200K	1
81	Nova 2.0 Pro Preview (medium)Amazon	21.8	34	7	$0.183	33s	256K	1
82	Gemma 4 31BOpenGoogle	21.8	33.2	11	$0.034	10.0s	262K	8
83	Gemma 4 12B (Reasoning)OpenGoogle	21.8	31	7.9	$0.067	1.6 min	262K	1
84	Mercury 2Inception	21.4	31.1	9.6	$0.079	4.0s	128K	1
85	Qwen3.5 9B (Reasoning)OpenAlibaba	21.4	28.7	7.4	$0.243	42s	262K	2
86	Qwen3 Coder NextOpenAlibaba	21.1	36.2	8.8	$0.330	5.2s	262K	3
87	Qwen3.5 4B (Reasoning)OpenAlibaba	20.1	22.6	N/A	N/A	2.0 min	262K	1
88	Gemma 4 26B A4BOpenGoogle	20.1	N/A	N/A	N/A	11s	1.0M	6
89	North Mini CodeOpenCohere	19.8	36.5	3.1	$0.0000	1.7 min	256K	1
90	Mistral Small 4 (Reasoning)OpenMistral	19.6	26.6	4.7	$0.101	17s	256K	1
91	Nova 2.0 Pro Preview (low)Amazon	19.6	25.9	6.4	$0.213	32s	256K	1
92	Devstral 2OpenMistral	19.2	31.3	10.6	$0.0000	11s	262K	1
93	Qwen3.5 Omni FlashOpenAlibaba	19	N/A	N/A	N/A	4.0s	256K	1
94	Nova 2.0 Lite (medium)Amazon	19	N/A	N/A	N/A	35s	1.0M	1
95	Nova 2.0 Lite (high)Amazon	18.2	23	3.1	$0.241	40s	1.0M	1
96	Trinity Large ThinkingOpenArcee AI	18.2	25.8	3.7	$0.148	13s	262K	2
97	Magistral Medium 1.2OpenMistral	17.9	21.3	1.9	$0.844	60s	131K	1
98	HyperNova 60B 2605OpenMultiverse Computing	17.8	23.2	6.7	$0.023	7.3s	131K	1
99	Nova 2.0 Lite (low)Amazon	17.8	N/A	N/A	N/A	27s	1.0M	1
100	Devstral Small 2OpenMistral	17.4	29.3	10.5	$0.0000	12s	256K	1
101	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.7	17.4	2.1	$0.170	15s	262K	3
102	Qwen3.5 4BOpenAlibaba	16	20.3	N/A	N/A	31s	262K	1
103	Mistral Large 3OpenMistral	15.9	20.1	5.5	$0.081	12s	262K	3
104	gpt-oss-20b (high)OpenOpenAI	14.9	20.7	3.1	$0.029	15s	131K	9
105	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	13.8	N/A	N/A	9.2s	66K	1
106	gpt-oss-120b (low)OpenOpenAI	14.9	21.2	1	$0.017	12s	131K	14
107	Nova 2.0 Pro PreviewAmazon	14.4	20.9	2.9	$0.259	6.5s	256K	1
108	gpt-oss-20b (low)OpenOpenAI	14.3	N/A	N/A	N/A	16s	131K	8
109	Llama 4 MaverickOpenMeta	14.3	16.3	1.3	$0.035	5.6s	1.0M	7
110	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	14.2	14.4	2	$0.025	10s	262K	3
111	Ling 2.6 FlashOpenInclusionAI	14.1	25.3	2.3	N/A	7.4s	262K	1
112	Solar Pro 3Upstage	14.1	16.2	2.7	$0.105	34s	131K	1
113	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	N/A	N/A	N/A	4.9s	262K	6
114	Gemma 4 12BOpenGoogle	13.2	N/A	N/A	N/A	22s	262K	1
115	Nova PremierAmazon	12.7	N/A	N/A	N/A	18s	1.0M	1
116	Mistral Small 4OpenMistral	12.4	N/A	N/A	N/A	4.4s	262K	1
117	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	12.4	N/A	N/A	N/A	38s	131K	1
118	Gemma 4 E4B (Reasoning)OpenGoogle	12.2	9.4	1.8	$0.013	28s	262K	1
119	Nova 2.0 LiteAmazon	11.8	N/A	N/A	N/A	4.6s	1.0M	1
120	Magistral Small 1.2OpenMistral	11.3	14.7	1.4	$0.286	29s	131K	2

Showing 120 of 155 models.

How to use this LLM ranking page

Start with capability, then force the economics

Frontier models often cluster tightly on raw intelligence. Cost per task, response time, provider coverage, and context length usually create the real shortlist.

Move from discovery to a defensible final pick

Use Explore to find the shape of the market, then move into Compare or use the Agentic Fit Finder when task-level reliability and cost matter more than chat quality alone.

Frequently Asked Questions

What is the best LLM in 2026?

Claude Opus 5 leads the overall quality ranking right now. The best model for you depends on your use case — coding, cost, speed, and context length all shift the answer.

How do I compare LLMs?

Sort by Quality Index for overall strength, then filter by price, speed, or context window to match your constraints. Move to the Compare page to put 2–4 finalists head to head.

Which AI model has the best quality-to-price ratio?

Open-weight models like DeepSeek, Qwen, and Llama often lead on quality-to-price. For agentic workflows, cost per task is usually a better filter than token price alone.

How often is this leaderboard updated?

Data is pulled from Artificial Analysis and refreshed automatically. New models appear as soon as they have benchmark scores and provider endpoints.

Model rankings

Current live rankings

Browse the latest ranking pages for overall models, coding, local hardware, open source, Ollama, long context, and agentic workflows.

Coding

Best LLM for Coding

Current coding leaderboard using LiveCodeBench, Terminal-Bench, and SciCode.

Open page →

Open Source

Best Open Source LLM

Top open-weight models for self-hosting, Ollama, and low-cost API use.

Open page →

Self-Hosted

Best Local LLM

Best local AI models by hardware tier for self-hosting on Macs, RTX GPUs, and workstations.

Open page →

Local Coding

Best Local LLM for Coding

Coding-focused local models mapped to 8GB, 24GB, 64GB, and server-class hardware.

Open page →

Ollama

Best Ollama Models

Ollama-first picks for coding, chat, reasoning, and low-friction local inference.

Open page →

Long Context

Largest Context Window LLM

Best long-context models for large documents, codebases, and retrieval-heavy workflows.

Open page →

Agents

Best Agentic Models

Rankings for tool use, multi-step execution, and autonomous agent workflows.

Open page →