Live Leaderboard

AI Model Rankings

Ranked by Intelligence Index — a composite quality score across reasoning, coding, math, and instruction following. Updated daily.

Last updated: 2026-05-24 · 100 models

#	Model	Org	Intelligence	Coding	Math	Speed	$/1M
1	GPT-5.5 (xhigh)2026-04-23	OpenAI	60.2	59.1	—	66 t/s	$11.25
2	GPT-5.5 (high)2026-04-23	OpenAI	58.9	58.5	—	72 t/s	$11.25
3	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)2026-04-16	Anthropic	57.3	52.5	—	55 t/s	$10.94
4	Gemini 3.1 Pro Preview2026-02-19	Google	57.2	55.5	—	132 t/s	$4.50
5	GPT-5.4 (xhigh)2026-03-05	OpenAI	56.8	57.2	—	102 t/s	$5.63
6	GPT-5.5 (medium)2026-04-23	OpenAI	56.7	56.2	—	71 t/s	$11.25
7	Qwen3.7 Max2026-05-19	Alibaba	56.6	50.1	—	203 t/s	$3.75
8	Gemini 3.5 Flash (high)2026-05-19	Google	55.3	45	—	219 t/s	$3.38
9	Kimi K2.62026-04-20	Kimi	53.9	47.1	—	52 t/s	$1.71
10	MiMo-V2.5-Pro2026-04-22	Xiaomi	53.8	45.5	—	57 t/s	$1.50
11	GPT-5.3 Codex (xhigh)2026-02-05	OpenAI	53.6	53.1	—	81 t/s	$4.81
12	Grok 4.3 (high)2026-04-30	xAI	53.2	41	—	125 t/s	$1.56
13	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)2026-02-05	Anthropic	52.9	48.1	—	48 t/s	$10.94
14	Muse Spark2026-04-08	Meta	52.2	47.5	—	0 t/s	$0.00
15	Claude Opus 4.7 (Non-reasoning, High Effort)2026-04-16	Anthropic	51.8	53.1	—	50 t/s	$10.94
16	Qwen3.6 Max Preview2026-04-20	Alibaba	51.8	44.9	—	34 t/s	$2.92
17	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)2026-02-17	Anthropic	51.7	50.9	—	75 t/s	$6.56
18	DeepSeek V4 Pro (Reasoning, Max Effort)2026-04-24	DeepSeek	51.5	47.5	—	36 t/s	$0.54
19	GLM-5.1 (Reasoning)2026-04-07	Z AI	51.4	43.4	—	64 t/s	$2.15
20	GPT-5.2 (xhigh)2025-12-11	OpenAI	51.3	48.7	99	79 t/s	$4.81
21	GPT-5.5 (low)2026-04-23	OpenAI	50.8	52.1	—	68 t/s	$11.25
22	Qwen3.6 Plus2026-04-02	Alibaba	50	42.9	—	53 t/s	$1.13
23	DeepSeek V4 Pro (Reasoning, High Effort)2026-04-24	DeepSeek	49.8	43.2	—	34 t/s	$0.54
24	GLM-5 (Reasoning)2026-02-11	Z AI	49.8	44.2	—	72 t/s	$1.55
25	Claude Opus 4.5 (Reasoning)2025-11-24	Anthropic	49.7	47.8	91.3	64 t/s	$10.94
26	MiniMax-M2.72026-03-18	MiniMax	49.6	41.9	—	51 t/s	$0.53
27	Grok 4.20 0309 v2 (Reasoning)2026-04-07	xAI	49.3	40.5	—	112 t/s	$3.00
28	MiMo-V2-Pro2026-03-18	Xiaomi	49.2	41.4	—	61 t/s	$1.50
29	MiMo-V2.52026-04-22	Xiaomi	49	42.1	—	95 t/s	$0.72
30	GPT-5.2 Codex (xhigh)2025-12-11	OpenAI	49	43	—	101 t/s	$4.81
31	GPT-5.4 mini (xhigh)2026-03-17	OpenAI	48.9	51.5	—	156 t/s	$1.69
32	Grok 4.3 (medium)2026-04-30	xAI	48.8	35.1	—	114 t/s	$1.56
33	Grok 4.20 0309 (Reasoning)2026-03-10	xAI	48.5	42.2	—	111 t/s	$3.00
34	Gemini 3 Pro Preview (high)2025-11-18	Google	48.4	46.5	95.7	135 t/s	$4.50
35	GPT-5.4 (low)2026-03-05	OpenAI	47.9	45.6	—	69 t/s	$5.63
36	GPT-5.1 (high)2025-11-13	OpenAI	47.7	44.7	94	131 t/s	$3.44
37	GLM-5-Turbo2026-03-15	Z AI	46.8	36.8	—	0 t/s	$0.00
38	Kimi K2.5 (Reasoning)2026-01-27	Kimi	46.8	39.6	—	36 t/s	$1.19
39	GPT-5.2 (medium)2025-12-11	OpenAI	46.6	44.2	96.7	0 t/s	$4.81
40	DeepSeek V4 Flash (Reasoning, Max Effort)2026-04-24	DeepSeek	46.5	38.7	—	110 t/s	$0.17
41	Claude Opus 4.6 (Non-reasoning, High Effort)2026-02-05	Anthropic	46.5	47.6	—	49 t/s	$10.94
42	Gemini 3 Flash Preview (Reasoning)2025-12-17	Google	46.4	42.6	97	202 t/s	$1.13
43	DeepSeek V4 Flash (Reasoning, High Effort)2026-04-24	DeepSeek	46	39.8	—	0 t/s	$0.17
44	Qwen3.6 27B (Reasoning)2026-04-22	Alibaba	45.8	36.5	—	65 t/s	$1.35
45	Qwen3.5 397B A17B (Reasoning)2026-02-16	Alibaba	45	41.3	—	52 t/s	$1.35
46	MiMo-V2-Omni-03272026-03-27	Xiaomi	44.9	36.9	—	102 t/s	$0.80
47	GPT-5 (high)2025-08-07	OpenAI	44.6	36	94.3	89 t/s	$3.44
48	GPT-5 Codex (high)2025-09-23	OpenAI	44.6	38.9	98.7	182 t/s	$3.44
49	Claude Sonnet 4.6 (Non-reasoning, High Effort)2026-02-17	Anthropic	44.4	46.4	—	55 t/s	$6.56
50	GPT-5.4 nano (xhigh)2026-03-17	OpenAI	44	43.9	—	156 t/s	$0.46
51	Grok 4.3 (low)2026-04-30	xAI	43.9	31.6	—	99 t/s	$1.56
52	KAT Coder Pro V22026-03-27	KwaiKAT	43.8	45.6	—	107 t/s	$0.53
53	GLM-5.1 (Non-reasoning)2026-04-07	Z AI	43.8	35.8	—	45 t/s	$2.15
54	Qwen3.6 35B A3B (Reasoning)2026-04-16	Alibaba	43.5	35.2	—	167 t/s	$0.56
55	MiMo-V2-Omni2026-03-19	Xiaomi	43.4	35.5	—	101 t/s	$0.00
56	Gemini 3.5 Flash (minimal)2026-05-19	Google	43.3	47.1	—	216 t/s	$3.38
57	GPT-5.1 Codex (high)2025-11-13	OpenAI	43.1	36.6	95.7	183 t/s	$3.44
58	Claude Opus 4.5 (Non-reasoning)2025-11-24	Anthropic	43.1	42.9	62.7	58 t/s	$10.94
59	Claude 4.5 Sonnet (Reasoning)2025-09-29	Anthropic	43	38.6	88	57 t/s	$6.56
60	Kimi K2.6 (Non-reasoning)2026-04-20	Kimi	42.9	38.4	—	64 t/s	$1.71
61	GLM 5V Turbo (Reasoning)2026-04-01	Z AI	42.9	36.2	—	0 t/s	$0.00
62	Claude Sonnet 4.6 (Non-reasoning, Low Effort)2026-02-17	Anthropic	42.6	43	—	53 t/s	$6.56
63	GLM-4.7 (Reasoning)2025-12-22	Z AI	42.1	36.3	95	89 t/s	$1.00
64	Qwen3.5 27B (Reasoning)2026-02-24	Alibaba	42.1	34.9	—	89 t/s	$0.82
65	GPT-5 (medium)2025-08-07	OpenAI	42	38.9	91.7	93 t/s	$3.44
66	Claude 4.1 Opus (Reasoning)2025-08-05	Anthropic	42	36.5	80.3	38 t/s	$32.81
67	Hy3-preview (Reasoning)2026-04-23	Tencent	41.9	36.5	—	91 t/s	$0.20
68	MiniMax-M2.52026-02-12	MiniMax	41.9	37.4	—	96 t/s	$0.53
69	DeepSeek V3.2 (Reasoning)2025-12-01	DeepSeek	41.7	36.7	92	0 t/s	$0.34
70	Qwen3.5 122B A10B (Reasoning)2026-02-24	Alibaba	41.6	34.7	—	146 t/s	$1.10
71	MiMo-V2-Flash (Feb 2026)2025-12-16	Xiaomi	41.5	33.5	—	132 t/s	$0.15
72	Grok 42025-07-10	xAI	41.5	40.5	92.7	0 t/s	$11.00
73	Gemini 3 Pro Preview (low)2025-11-18	Google	41.3	39.4	86.7	0 t/s	$4.50
74	GPT-5 mini (high)2025-08-07	OpenAI	41.2	35.3	90.7	102 t/s	$0.69
75	GPT-5.5 (Non-reasoning)2026-04-23	OpenAI	40.9	48.6	—	64 t/s	$11.25
76	Kimi K2 Thinking2025-11-06	Kimi	40.9	34.8	94.7	110 t/s	$1.07
77	o3-pro2025-06-10	OpenAI	40.7	—	—	22 t/s	$35.00
78	GLM-5 (Non-reasoning)2026-02-11	Z AI	40.6	39	—	60 t/s	$1.55
79	Qwen3.5 397B A17B (Non-reasoning)2026-02-16	Alibaba	40.1	37.4	—	51 t/s	$1.35
80	Qwen3 Max Thinking2026-01-26	Alibaba	39.8	30.5	—	43 t/s	$2.40
81	MiniMax-M2.12025-12-23	MiniMax	39.4	32.8	82.7	88 t/s	$0.53
82	DeepSeek V4 Pro (Non-reasoning)2026-04-24	DeepSeek	39.3	38.4	—	36 t/s	$0.54
83	Gemma 4 31B (Reasoning)2026-04-02	Google	39.2	38.7	—	35 t/s	$0.00
84	Mistral Medium 3.52026-04-29	Mistral	39.2	35.4	—	147 t/s	$3.00
85	GPT-5 (low)2025-08-07	OpenAI	39.2	30.7	83	79 t/s	$3.44
86	MiMo-V2-Flash (Reasoning)2025-12-16	Xiaomi	39.2	31.8	96.3	133 t/s	$0.15
87	Claude 4 Opus (Reasoning)2025-05-22	Anthropic	39	34	73.3	42 t/s	$32.81
88	GPT-5 mini (medium)2025-08-07	OpenAI	38.9	32.8	85	95 t/s	$0.69
89	Claude 4 Sonnet (Reasoning)2025-05-22	Anthropic	38.7	34.1	74.3	55 t/s	$6.56
90	Grok 4.1 Fast (Reasoning)2025-11-19	xAI	38.6	30.9	89.3	0 t/s	$0.00
91	Qwen3.5 Omni Plus2026-03-30	Alibaba	38.6	27.6	—	53 t/s	$1.50
92	GPT-5.1 Codex mini (high)2025-11-13	OpenAI	38.6	36.4	91.7	216 t/s	$0.69
93	Step 3.5 Flash 26032026-04-02	StepFun	38.5	34.6	—	161 t/s	$0.00
94	Ring-2.6-1T2026-05-08	InclusionAI	38.5	33.3	—	0 t/s	$0.00
95	o32025-04-16	OpenAI	38.4	38.4	88.3	124 t/s	$3.50
96	GPT-5.4 nano (medium)2026-03-17	OpenAI	38.1	35	—	146 t/s	$0.46
97	Step 3.5 Flash2026-02-02	StepFun	37.8	31.6	—	161 t/s	$0.15
98	GPT-5.4 mini (medium)2026-03-17	OpenAI	37.7	37.5	—	162 t/s	$1.69
99	Kimi K2.5 (Non-reasoning)2026-01-27	Kimi	37.3	25.8	—	32 t/s	$1.20
100	Command A+2026-05-20	Cohere	37.2	29.3	—	201 t/s	$0.00

Get the weekly AI Rankings digest

Top movers, new models, and what changed — every Monday.

About this ranking

Intelligence Index is a composite quality score aggregating performance across reasoning, coding, math, and instruction-following benchmarks into a single comparable number. Pricing and speed are measured by running models at scale under controlled conditions.

Data source: Artificial Analysis — independent AI benchmarking. Intelligence Index, benchmark scores, pricing, and speed data are © Artificial Analysis. DruxAI fetches this data daily via the Artificial Analysis API and does not modify or influence the scores.

Model and creator identifiers used per Artificial Analysis API guidelines.