Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	New	Gemini 4 Carbon (High)ClosedGoogle	59.4	$8.0	94	148 s
2	▼ 1	Claude Opus 5.5 (Max, Default Fallback)ClosedAnthropic	58.4	$8.0	96	626 s
3	New	Gemini 4 Carbon (Medium)ClosedGoogle	57.7	$8.0	101	29 s
4	▼ 1	Claude Opus 5.5 (Xhigh, Default Fallback)ClosedAnthropic	57.0	$8.0	81	110 s
5	▲ 4	GPT-6 Astra (Max)ClosedOpenAI	56.9	$20	71	369 s
6	▲ 6	GPT-6 Astra (Xhigh)ClosedOpenAI	55.3	$20	68	203 s
7	▲ 11	GPT-6 Astra (High)ClosedOpenAI	54.8	$20	62	107 s
8	▲ 6	GPT-6.1 Sol (Max)ClosedOpenAI	54.5	$4.0	93	308 s
9	▼ 7	Claude Sonnet 5.5 (Max, Default Fallback)ClosedAnthropic	54.2	$4.0	139	456 s
10	New	Gemini 4 Carbon (Low)ClosedGoogle	53.7	$8.0	—	—
11	▲ 6	GPT-6.1 Sol (Xhigh)ClosedOpenAI	52.3	$4.0	78	153 s
12	▼ 6	Claude Opus 5.5 (High, Default Fallback)ClosedAnthropic	51.7	$8.0	80	44 s
13	▲ 7	GPT-6 Astra (Medium)ClosedOpenAI	51.5	$20	55	6.0 s
14	New	GPT-6.1 Terra (Max)ClosedOpenAI	51.0	$2.0	111	275 s
15	▼ 5	Gemini 4 Argon (High)ClosedGoogle	50.4	$8.0	83	40 s
16	▲ 3	GPT-6.1 Sol (High)ClosedOpenAI	50.2	$4.0	71	70 s
17	▼ 13	Muse Wonder Full (Max)ClosedMeta	49.7	—	—	—
18	▼ 10	Claude Fable 5.1 (Xhigh, Default Fallback)ClosedAnthropic	49.7	$20	63	76 s
19	▼ 6	Claude Sonnet 5.5 (Xhigh, Default Fallback)ClosedAnthropic	49.6	$4.0	107	36 s
20	▼ 13	Claude Fable 5.1 (Max, Default Fallback)ClosedAnthropic	49.0	$20	70	253 s
21	▼ 6	Claude Opus 5.5 (Medium, Default Fallback)ClosedAnthropic	48.1	$8.0	81	22 s
22	▼ 6	Claude Fable 5.1 (High, Default Fallback)ClosedAnthropic	47.0	$20	58	19 s
23	▼ 1	GPT-6.1 Sol (Medium)ClosedOpenAI	46.1	$4.0	63	8.9 s
24	▼ 19	Kimi K3.1 ProClosedKimi	46.0	$4.0	32	3.4 s
25	New	GPT-6.1 Terra (Xhigh)ClosedOpenAI	45.0	$2.0	104	68 s
26	▼ 15	Muse Wonder (Max)ClosedMeta	43.3	$8.0	196	28 s
27	▲ 1	GPT-6 Astra (Low)ClosedOpenAI	43.0	$20	54	2.6 s
28	▼ 7	Claude Fable 5.1 (Medium, Default Fallback)ClosedAnthropic	43.0	$20	58	14 s
29	New	GPT-6.1 Terra (High)ClosedOpenAI	42.3	$2.0	94	21 s
30	▼ 6	Claude Sonnet 5.5 (High, Default Fallback)ClosedAnthropic	41.1	$4.0	108	14 s
31	▼ 8	Claude Fable 5.1 (Low, Default Fallback)ClosedAnthropic	38.5	$20	56	2.8 s
32	New	GPT-6.1 Terra (Medium)ClosedOpenAI	38.1	$2.0	91	4.2 s
33	▲ 1	Claude Haiku 5.5 (Max)ClosedAnthropic	36.2	$0.20	235	334 s
34	▼ 9	Grok 4.7 (Xhigh)ClosedSpaceXAI	35.3	$3.0	86	109 s
35	▼ 9	Grok 4.7 (High)ClosedSpaceXAI	35.0	$3.0	76	66 s
36	▲ 2	GPT-6.1 Sol (Low)ClosedOpenAI	34.5	$4.0	62	2.5 s
37	▼ 1	Claude Opus 5.5 (Low, Default Fallback)ClosedAnthropic	34.5	$8.0	79	11 s
38	▲ 3	Claude Haiku 5.5 (Xhigh)ClosedAnthropic	34.3	$0.20	194	63 s
39	▼ 10	Qwen3.8 Max (0902)ClosedAlibaba	33.6	$3.0	38	3.0 s
40	▼ 10	DeepSeek V4.1 Flash 1017 (Max)OpenDeepSeek	32.5	$0.52	174	1.2 s
41	▼ 10	GLM-5.3 (Max)OpenZ AI	31.7	$2.2	90	1.4 s
42	▼ 5	Grok 4.7 (Low)ClosedSpaceXAI	30.9	$3.0	68	6.6 s
43	—	Gemini 3.8 Flash (High)ClosedGoogle	30.5	$1.5	137	25 s
44	New	GPT-6.1 Terra (Non-reasoning)ClosedOpenAI	30.4	$2.0	91	0.9 s
45	▼ 1	Claude Sonnet 5.5 (Medium, Default Fallback)ClosedAnthropic	30.3	$4.0	101	1.1 s
46	▲ 1	Gemini 3.8 Flash (Medium)ClosedGoogle	30.0	$1.5	—	—
47	▼ 20	MiMo-V2.6-ProOpenXiaomi	29.9	$0.54	44	3.5 s
48	▲ 5	Claude Haiku 5.5 (High)ClosedAnthropic	29.6	$0.20	184	32 s
49	▼ 17	Ling 3.1 Flash 1019OpenInclusionAI	29.5	$0.45	—	—
50	New	GPT-6.1 Terra (Low)ClosedOpenAI	29.2	$2.0	91	1.5 s
51	▼ 16	MiniMax-M3.1-FlashOpenMiniMax	28.9	$0.26	120	0.9 s
52	New	DeepSeek V4.1 Flash 1017 (High)OpenDeepSeek	28.5	$0.52	218	1.0 s
53	▼ 20	Step 5 PreviewOpenStepFun	28.5	$1.4	142	0.9 s
54	▼ 4	GPT-6 Luna (Max)ClosedOpenAI	27.8	$0.20	117	120 s
55	▼ 15	GLM-5.3-FlashOpenZ AI	27.8	$0.24	74	1.5 s
56	▼ 4	MiMo-V2.6-FlashOpenXiaomi	26.7	$0.18	36	2.7 s
57	New	Mistral Large 4 (High)OpenMistral	26.0	$1.0	—	—
58	▼ 3	Claude Sonnet 5.5 (Low, Default Fallback)ClosedAnthropic	25.3	$4.0	106	1.2 s
59	▼ 11	Muse Spark Open (Xhigh)OpenMeta	24.7	$2.0	188	0.7 s
60	▼ 1	Claude Haiku 5.5 (Medium)ClosedAnthropic	24.6	$0.20	176	14 s
61	▼ 3	GPT-6 Luna (Xhigh)ClosedOpenAI	23.3	$0.20	129	36 s
62	New	Mistral Large 4 (Medium)OpenMistral	23.1	$1.0	—	—
63	▼ 9	DeepSeek V4 Pro 0813 (Max)OpenDeepSeek	23.1	$2.0	83	1.8 s
64	▼ 4	GLM-5.3 (Low)OpenZ AI	23.1	$2.2	84	1.7 s
65	—	Gemini 3.8 Flash (Low)ClosedGoogle	22.3	$1.5	—	—
66	—	GPT-6 Luna (High)ClosedOpenAI	21.4	$0.20	121	27 s
67	New	Nanbeige4.3-33BOpenNanbeige	20.4	—	—	—
68	▼ 5	Qwen3.8 27B (Xhigh)OpenAlibaba	20.1	$1.1	41	4.0 s
69	▲ 5	MiniMax-M3OpenMiniMax	18.7	$0.52	112	0.8 s
70	▲ 3	Claude Haiku 5.5 (Low)ClosedAnthropic	18.6	$0.20	167	8.9 s
71	New	DeepSeek V4.1 Flash 1017 (Non-reasoning)OpenDeepSeek	18.5	$0.52	185	1.4 s
72	▼ 1	GPT-6 Luna (Medium)ClosedOpenAI	18.3	$0.20	—	—
73	▼ 5	K2 Horizon 375B A23BOpenInstitute of Foundation Models	17.8	$0.000	665	2.4 s
74	▼ 5	Beam 1.0OpenReflection	17.7	$0.60	357	0.7 s
75	▲ 1	Qwen3.8 27B (Medium)OpenAlibaba	17.5	$1.1	48	4.0 s
76	▲ 7	Qwen3.8 27B (Low)OpenAlibaba	15.7	$1.1	47	4.1 s
77	▲ 4	Nemotron 3.5 Super VLOpenNVIDIA	13.6	$0.28	464	0.7 s
78	▲ 8	Inkling SmallOpenThinking Machines	12.9	$0.52	226	1.6 s
79	▲ 11	Inkling (Xhigh)OpenThinking Machines	12.5	$1.8	211	1.7 s
80	▲ 14	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	11.8	$1.1	163	1.2 s
81	▲ 15	Gemini 3.5 Flash-LiteClosedGoogle	11.7	$0.85	442	6.4 s
82	▲ 26	Qwen3.8 27B (Non-reasoning)OpenAlibaba	10.0	$1.1	45	4.0 s
83	▲ 16	GPT-6 Luna (Low)ClosedOpenAI	9.7	$0.20	115	2.5 s
84	▲ 28	GPT-6 Luna (Non-reasoning)ClosedOpenAI	9.4	$0.20	110	0.8 s
85	▲ 31	Muse Glimmer (High)OpenMeta	6.3	$0.52	126	1.1 s
86	▲ 48	Command A+OpenCohere	6.2	$0.000	176	0.5 s
87	▲ 50	Nemotron 3.5 LightningOpenNVIDIA	5.5	$0.095	295	0.6 s
88	▲ 69	Granite 4.2 8BOpenIBM	5.1	$0.11	61	1.0 s
89	▲ 89	Granite 4.2 3BOpenIBM	4.7	—	—	—
90	▲ 63	Mistral Small 4 (Reasoning)OpenMistral	4.3	$0.26	170	0.9 s
91	▲ 174	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	1.8	—	—	—

41 more models

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026

64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi