LLM Leaderboard 2026: Rank & Compare 100+ AI Models Live

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.

Model discovery workbench

Move from a crowded market to a defensible shortlist. Rank models by capability, task economics, speed, context, and real provider availability.

Models: 162
Providers: 99
Data snapshot: Sep 30, 2026, 16:27 UTC
Method: Index v4.3
Latest tracked: Oct 1, 2026

Rank by

Show

Model rankings

146 results · sorted by intelligence

Underlined names open model pages. Use the chevron for endpoint details.

#
1	Claude Opus 5.5Anthropic	57.6	N/A	N/A	$0.551	14s	1.0M	3
2	Claude Sonnet 5.5Anthropic	56	N/A	N/A	$0.417	6.3s	1.0M	3
3	Claude Fable 5.1Anthropic	53.4	81.6	57.9	$2.37	13s	1.0M	1
4	GPT-6 AstraOpenAI	52.7	76.9	51	$3.26	4.9 min	1.0M	3
5	GPT-6 Astra (Xhigh)OpenAI	52.4	75.9	50.2	$2.31	2.5 min	1.0M	1
6	GPT-6.1 SolOpenAI	51.8	N/A	N/A	$0.724	4.7 min	1.0M	1
7	GPT-6.1 Sol (Xhigh)OpenAI	51	N/A	N/A	$0.393	2.8 min	1.0M	1
8	GPT-6 Astra (High)OpenAI	50.9	77.1	48.2	$1.73	89s	1.0M	1
9	GPT-6.1 Sol (High)OpenAI	50.2	N/A	N/A	$0.319	60s	1.0M	1
10	GPT-6 Astra (Medium)OpenAI	49.6	76.7	46	$1.54	15s	1.0M	1
11	Muse Spark 1.3OpenMeta	48.1	75.8	55.5	$1.60	65s	1.0M	1
12	GPT-6.1 Sol (Medium)OpenAI	47.8	N/A	N/A	$0.214	16s	1.0M	1
13	Grok 4.7 (Xhigh)SpaceXAI	46.4	N/A	N/A	$3.74	49s	500K	1
14	MiMo-V2.6-ProOpenXiaomi	46.3	N/A	N/A	$0.133	62s	1.0M	4
15	Grok 4.7 (High)SpaceXAI	46.3	N/A	N/A	$2.73	44s	500K	1
16	GPT-6 Astra (Low)OpenAI	45.8	75.7	38.8	$0.818	12s	1.0M	2
17	Qwen3.8 MaxOpenAlibaba	45.4	76.2	56	$5.41	70s	984K	1
18	Muse Spark 1.3 (Xhigh)OpenMeta	45.1	76.5	51.5	$1.37	45s	1.0M	1
19	GLM-5.3OpenZ AI	44.8	74.8	53.1	$2.01	38s	1.0M	23
20	Step 5 PreviewStepFun	43.7	N/A	N/A	$0.718	31s	1.0M	1
21	Kimi K3OpenKimi	43.6	76.2	50	$2.00	61s	1.0M	15
22	Grok 4.7 (Low)SpaceXAI	42.2	N/A	N/A	$1.25	12s	500K	1
23	GPT-5.6 TerraOpenAI	42.1	76.7	43.2	$0.140	5.8s	1.0M	2
24	GPT-6.1 Sol (Low)OpenAI	42.1	N/A	N/A	$0.131	13s	1.0M	1
25	GLM 5.3 FlashOpenZ AI	41.8	71.5	50.9	$0.253	51s	1.0M	21
26	Ling 3.1 FlashOpenInclusionAI	41.1	N/A	N/A	$0.986	14s	1.0M	1
27	Gemini 3.8 Flash (High)Google	40.9	76.3	40.2	$1.24	15s	1.0M	1
28	Qwen3.8 2.4T A95BOpenAlibaba	39.9	71.9	50.1	$2.16	69s	1.0M	6
29	Qwen3.8-Flash-NextOpenAlibaba	39.8	73.1	53.6	$0.372	48s	1.0M	1
30	DeepSeek V4.1 FlashOpenDeepSeek	39.5	N/A	N/A	$0.147	3.3s	1.0M	21
31	GPT-6 LunaOpenAI	38.1	N/A	N/A	$0.011	4.5s	1.0M	2
32	GPT-5.6 Terra (Xhigh)OpenAI	38	70.6	41.4	$0.632	34s	1.0M	2
33	MiMo-V2.6-FlashOpenXiaomi	37.9	N/A	N/A	$0.062	51s	1.0M	3
34	DeepSeek V4 Pro 0813OpenDeepSeek	36	68.8	41.3	$0.330	4.5s	1.0M	9
35	DeepSeek V4 Flash VisionOpenDeepSeek	34.8	65	47.5	$0.314	12s	1.0M	4
36	GPT-6 Luna (Xhigh)OpenAI	34.6	N/A	N/A	$0.042	30s	1.0M	1
37	GLM-5.3 (Low)OpenZ AI	34.3	N/A	N/A	$0.852	34s	1.0M	4
38	GPT-5.6 Terra (High)OpenAI	34.2	67.1	36.7	$0.338	7.8s	1.0M	2
39	Qwen3.8 27B (Xhigh)OpenAlibaba	33.7	68.1	45.8	$1.01	59s	1.0M	8
40	GPT-6 Luna (High)OpenAI	32.9	N/A	N/A	$0.029	18s	1.0M	1
41	GPT-5.3 Codex (Xhigh)OpenAI	32.5	N/A	N/A	N/A	74s	400K	1
42	K2 Horizon 375B A23BOpenInstitute of Foundation Models	30.5	61.5	40	$0.0000	41s	524K	1
43	GPT-5.6 Terra (Medium)OpenAI	30.1	64.7	30.4	$0.183	6.5s	1.0M	1
44	Kimi K3 (Low)OpenKimi	30.1	72	29.3	$1.15	61s	1.0M	3
45	Gemini 3.1 Pro PreviewGoogle	29.7	68.8	8.2	$0.675	28s	1.0M	2
46	MiniMax-M3OpenMiniMax	29.2	58.6	29.5	$0.508	28s	1.0M	13
47	Solar Pro 4Upstage	28.2	52.7	N/A	N/A	25s	512K	1
48	Qwen3.8 27B (Medium)OpenAlibaba	27.6	56.1	44.4	$1.13	52s	1.0M	2
49	GPT-5.6 Terra (Low)OpenAI	27.5	58.1	25.9	$0.144	6.9s	1.0M	1
50	Quasar 438BOpenMultiverse Computing	26.7	61.2	31.4	$2.02	17s	1.0M	1
51	Qwen3.8 27B (Low)OpenAlibaba	26.2	58.2	38.9	$1.05	53s	1.0M	2
52	GPT-5.5 InstantOpenAI	26	39.4	16.6	$0.692	22s	400K	1
53	Kimi K2.7 CodeOpenKimi	25.8	60.8	21	$0.541	31s	262K	6
54	Inkling SmallOpenThinking Machines	25.7	52.9	23.5	$0.089	15s	524K	2
55	Hy3OpenTencent	25.3	58.8	24.1	$0.072	31s	262K	4
56	Qwen3.7 PlusOpenAlibaba	25.2	55.9	17.5	$0.217	47s	1.0M	1
57	Inkling (Xhigh)OpenThinking Machines	25	52.1	22.5	N/A	16s	1.0M	5
58	Ling-3.0-flash-VLOpenInclusionAI	24.6	57	28.7	N/A	N/A	262K	1
59	Solar Mini 4Upstage	24.1	N/A	N/A	$0.363	N/A	524K	1
60	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	22.9	49.3	20.1	$0.598	17s	262K	4
61	Ling-3.0-flash-FinOpenInclusionAI	22.6	55.6	27.9	N/A	9.2s	262K	1
62	Gemini 3.5 Flash-LiteGoogle	22.2	49.3	14.3	$0.123	11s	1.0M	1
63	GPT-6 Luna (Low)OpenAI	21.5	N/A	N/A	$0.0045	6.0s	1.0M	1
64	Qwen3.5 397B A17BOpenAlibaba	21.4	N/A	N/A	N/A	8.2s	262K	5
65	Qwen3.5 Omni PlusOpenAlibaba	20.4	N/A	N/A	N/A	6.5s	256K	1
66	o3OpenAI	20.2	N/A	N/A	N/A	12s	200K	2
67	Qwen3.8 27BOpenAlibaba	20.2	44.6	22.4	$2.49	14s	1.0M	5
68	Ling 3.0 FlashOpenInclusionAI	20.1	50.6	19.3	N/A	9.8s	262K	2
69	LongCat 2.0OpenLongCat	19.1	45.3	14	$0.059	N/A	262K	1
70	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	18.4	48.2	8.3	$0.475	45s	262K	6
71	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	18.2	41.9	13.1	$0.475	47s	262K	7
72	Qwen3.5 122B A10BOpenAlibaba	17.7	43.3	N/A	N/A	5.8s	262K	2
73	Muse Glimmer (High)OpenMeta	17.5	49	8.5	$0.057	19s	131K	3
74	Claude 4.5 Haiku (Reasoning)Anthropic	16.9	43.9	8	$0.277	23s	200K	4
75	Gemma 4 26B A4B (Reasoning)OpenGoogle	16.7	39.3	2.9	N/A	N/A	1.0M	7
76	Ring-2.6-1TOpenInclusionAI	16.6	42.8	10.7	$0.287	25s	262K	1
77	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	15.6	45.7	7.6	$0.325	22s	262K	4
78	Claude 4.5 HaikuAnthropic	15.4	N/A	N/A	N/A	6.4s	200K	4
79	Qwen3.6 35B A3BOpenAlibaba	15.2	28.1	N/A	N/A	5.8s	262K	6
80	Granite 4.2 30BOpenIBM	14.8	29.9	N/A	N/A	33s	131K	1
81	Gemma 4 31B (Reasoning)OpenGoogle	14.7	43.4	4.2	$0.0000	64s	262K	10
82	Nova 2.0 Pro Preview (Medium)Amazon	14.2	34	N/A	N/A	33s	256K	1
83	Mistral Medium 3.5OpenMistral	14.2	46.9	7	$0.502	17s	262K	1
84	Gemma 4 12B (Reasoning)OpenGoogle	14.2	31	N/A	N/A	25s	262K	1
85	Gemma 4 31BOpenGoogle	13.9	33.2	N/A	N/A	14s	262K	9
86	Nova 2.0 Lite (High)Amazon	13.4	23	N/A	N/A	30s	1.0M	1
87	Qwen3.5 9BOpenAlibaba	13.3	23.5	N/A	N/A	5.9s	262K	1
88	Command A+OpenCohere	13.1	27.8	1	$0.0000	17s	200K	1
89	Qwen3.5 4B (Reasoning)OpenAlibaba	13.1	22.6	N/A	N/A	2.3 min	262K	1
90	Gemma 4 26B A4BOpenGoogle	13.1	N/A	N/A	N/A	6.2s	1.0M	8
91	Nemotron 3.5 LightningOpenNVIDIA	12.9	26.8	3.5	$0.093	8.9s	1.0M	5
92	Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	12.8	37.7	1.7	$1.64	17s	262K	3
93	Nova 2.0 Pro Preview (Low)Amazon	12.8	25.9	N/A	N/A	29s	256K	1
94	Qwen3.5 Omni FlashOpenAlibaba	12.5	N/A	N/A	N/A	4.1s	256K	1
95	Nova 2.0 Lite (Medium)Amazon	12.5	N/A	N/A	N/A	34s	1.0M	1
96	Mercury 2.5Inception	12.3	N/A	N/A	$0.117	4.3s	256K	1
97	Nova 2.0 Lite (Low)Amazon	11.8	N/A	N/A	N/A	26s	1.0M	1
98	gpt-oss-120b (High)OpenOpenAI	11.6	30.4	3.7	$0.107	14s	131K	15
99	Mistral Small 4 (Reasoning)OpenMistral	11.3	26.6	0.8	$0.015	15s	256K	1
100	Qwen3.5 9B (Reasoning)OpenAlibaba	11.2	28.7	1.2	$0.213	39s	262K	2
101	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	11.2	17.4	N/A	N/A	15s	262K	2
102	Ling 3.0 TinyOpenInclusionAI	11.1	26.5	4.4	$0.0000	54s	262K	1
103	Granite 4.2 8BOpenIBM	11.1	22.4	1.3	$0.024	52s	131K	2
104	Qwen3.5 4BOpenAlibaba	10.8	20.3	N/A	N/A	34s	262K	1
105	Trinity Large ThinkingOpenArcee AI	10.8	25.8	1	$0.119	8.6s	262K	1
106	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	10.3	13.8	N/A	N/A	9.7s	262K	1
107	gpt-oss-120b (Low)OpenOpenAI	10.2	21.2	N/A	N/A	12s	131K	14
108	gpt-oss-20b (Low)OpenOpenAI	10	N/A	N/A	N/A	10s	131K	5
109	Llama 4 MaverickOpenMeta	10	16.3	0.6	N/A	8.5s	1.0M	4
110	Nova 2.0 Pro PreviewAmazon	10	20.9	N/A	N/A	5.6s	256K	1
111	North Mini CodeOpenCohere	9.9	36.5	1.1	$0.0000	28s	256K	1
112	Qwen3 Next 80B A3B InstructOpenAlibaba	9.6	N/A	N/A	N/A	5.0s	262K	6
113	Gemma 4 12BOpenGoogle	9.4	N/A	N/A	N/A	6.7s	262K	1
114	Mistral Large 3OpenMistral	9.3	20.1	1	$0.031	7.2s	262K	3
115	Qwen3 Coder NextOpenAlibaba	9.2	36.2	0.9	$0.552	6.5s	262K	3
116	Granite 4.2 3BOpenIBM	9.1	17.5	0.9	$0.0060	12s	131K	1
117	Mistral Small 4OpenMistral	9	N/A	N/A	N/A	3.8s	262K	1
118	gpt-oss-20b (High)OpenOpenAI	9	20.7	1.2	$0.013	13s	131K	6
119	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	8.9	14.4	1	$0.017	15s	262K	4
120	Gemma 4 E4B (Reasoning)OpenGoogle	8.9	N/A	N/A	N/A	66s	131K	1

1Claude Opus 5.5Anthropicintelligence57.6Task $0.551Response 14s1.0M context3 providers

2Claude Sonnet 5.5Anthropicintelligence56Task $0.417Response 6.3s1.0M context3 providers

3Claude Fable 5.1Anthropicintelligence53.4Task $2.37Response 13s1.0M context1 provider

4GPT-6 AstraOpenAIintelligence52.7Task $3.26Response 4.9 min1.0M context3 providers

5GPT-6 Astra (Xhigh)OpenAIintelligence52.4Task $2.31Response 2.5 min1.0M context1 provider

6GPT-6.1 SolOpenAIintelligence51.8Task $0.724Response 4.7 min1.0M context1 provider

7GPT-6.1 Sol (Xhigh)OpenAIintelligence51Task $0.393Response 2.8 min1.0M context1 provider

8GPT-6 Astra (High)OpenAIintelligence50.9Task $1.73Response 89s1.0M context1 provider

9GPT-6.1 Sol (High)OpenAIintelligence50.2Task $0.319Response 60s1.0M context1 provider

10GPT-6 Astra (Medium)OpenAIintelligence49.6Task $1.54Response 15s1.0M context1 provider

11Muse Spark 1.3OpenMetaintelligence48.1Task $1.60Response 65s1.0M context1 provider

12GPT-6.1 Sol (Medium)OpenAIintelligence47.8Task $0.214Response 16s1.0M context1 provider

13Grok 4.7 (Xhigh)SpaceXAIintelligence46.4Task $3.74Response 49s500K context1 provider

14MiMo-V2.6-ProOpenXiaomiintelligence46.3Task $0.133Response 62s1.0M context4 providers

15Grok 4.7 (High)SpaceXAIintelligence46.3Task $2.73Response 44s500K context1 provider

16GPT-6 Astra (Low)OpenAIintelligence45.8Task $0.818Response 12s1.0M context2 providers

17Qwen3.8 MaxOpenAlibabaintelligence45.4Task $5.41Response 70s984K context1 provider

18Muse Spark 1.3 (Xhigh)OpenMetaintelligence45.1Task $1.37Response 45s1.0M context1 provider

19GLM-5.3OpenZ AIintelligence44.8Task $2.01Response 38s1.0M context23 providers

20Step 5 PreviewStepFunintelligence43.7Task $0.718Response 31s1.0M context1 provider

21Kimi K3OpenKimiintelligence43.6Task $2.00Response 61s1.0M context15 providers

22Grok 4.7 (Low)SpaceXAIintelligence42.2Task $1.25Response 12s500K context1 provider

23GPT-5.6 TerraOpenAIintelligence42.1Task $0.140Response 5.8s1.0M context2 providers

24GPT-6.1 Sol (Low)OpenAIintelligence42.1Task $0.131Response 13s1.0M context1 provider

25GLM 5.3 FlashOpenZ AIintelligence41.8Task $0.253Response 51s1.0M context21 providers

26Ling 3.1 FlashOpenInclusionAIintelligence41.1Task $0.986Response 14s1.0M context1 provider

27Gemini 3.8 Flash (High)Googleintelligence40.9Task $1.24Response 15s1.0M context1 provider

28Qwen3.8 2.4T A95BOpenAlibabaintelligence39.9Task $2.16Response 69s1.0M context6 providers

29Qwen3.8-Flash-NextOpenAlibabaintelligence39.8Task $0.372Response 48s1.0M context1 provider

30DeepSeek V4.1 FlashOpenDeepSeekintelligence39.5Task $0.147Response 3.3s1.0M context21 providers

Showing 120 of 146 models.

Reading the field

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.

Field notes

Questions builders ask

What is the best LLM in 2026?

Claude Opus 5.5 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.

Ranking library

Current live rankings

Focused rankings for the decisions engineers actually make.

01CodingBest LLM for CodingLiveCodeBench, Terminal-Bench, SciCode, and engineering fit.Open ranking 02OpenBest Open Source LLMOpen-weight models for self-hosting and lower-cost deployment.Open ranking 03LocalBest Local LLMModels mapped to Mac, RTX, workstation, and server hardware.Open ranking 04Local codingBest Local LLM for CodingCoding strength filtered through realistic hardware limits.Open ranking 05OllamaBest Ollama ModelsLow-friction local models for coding, reasoning, and chat.Open ranking 06ContextLargest Context Window LLMLong documents, codebases, and retrieval-heavy work.Open ranking 07AgentsBest Agentic ModelsTool use, multi-step execution, and autonomous workflows.Open ranking