Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	New	GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants	60.2	$11	—	—
2	New	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	57.3	$10	42	17 s
3	▼ 2	Gemini 3.1 Pro PreviewClosedGoogle	57.2	$4.5	130	29 s
4	▼ 2	GPT-5.4 (xhigh)ClosedOpenAI · 1 more variant	56.8	$5.6	78	167 s
5	New	Kimi K2.6OpenKimi	53.9	$1.7	100	1.1 s
6	New	MiMo-V2.5-ProClosedXiaomi	53.8	$1.5	61	2.8 s
7	▼ 4	GPT-5.3 Codex (xhigh)ClosedOpenAI	53.6	$4.8	73	88 s
8	▼ 4	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	53.0	$10	41	8.6 s
9	▼ 4	Muse SparkClosedMeta	52.2	—	—	—
10	New	Qwen3.6 Max PreviewClosedAlibaba	51.8	$2.9	35	3.4 s
11	▼ 5	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	51.7	$6.0	48	127 s
12	▼ 5	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	49	1.5 s
13	▼ 5	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	51.3	$4.8	67	104 s
14	▼ 5	Qwen3.6 PlusClosedAlibaba	50.0	$1.1	53	3.0 s
15	▼ 5	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	70	1.7 s
16	▼ 5	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	49.7	$10	46	8.3 s
17	▼ 5	MiniMax-M2.7OpenMiniMax	49.6	$0.52	50	2.3 s
18	▼ 5	Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant	49.3	$3.0	164	16 s
19	▼ 5	MiMo-V2-ProClosedXiaomi	49.2	—	—	—
20	▼ 5	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	93	69 s
21	▼ 5	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	48.9	$1.7	164	8.9 s
22	▼ 5	Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant	48.5	$3.0	133	16 s
23	▼ 5	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	48.4	$4.5	134	28 s
24	▼ 5	GPT-5.1 (high)ClosedOpenAI · 1 more variant	47.7	$3.4	121	31 s
25	▼ 5	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.2	38	2.8 s
26	▼ 5	GLM-5-TurboClosedZ AI	46.8	—	—	—
27	New	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 1 more variant	46.5	$0.18	85	1.0 s
28	▼ 6	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	46.4	$1.1	169	7.1 s
29	New	Qwen3.6 27B (Reasoning)OpenAlibaba	45.8	$1.4	64	3.9 s
30	▼ 7	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.1	$1.4	53	2.4 s
31	▼ 7	MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant	44.9	—	—	—
32	▼ 7	GPT-5 (high)ClosedOpenAI · 4 more variants	44.6	$3.4	86	67 s
32	▼ 7	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	181	6.4 s
34	▼ 7	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	44.0	$0.46	154	3.7 s
35	New	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	43.5	$0.84	209	2.5 s
36	▼ 8	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	156	7.0 s
37	▼ 8	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	43.0	$6.0	40	9.3 s
38	▼ 8	GLM 5V Turbo (Reasoning)ClosedZ AI	42.9	—	—	—
39	▼ 8	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	103	1.2 s
40	▼ 8	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	80	5.7 s
41	▼ 8	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	42.0	$30	29	12 s
42	▼ 8	MiniMax-M2.5OpenMiniMax	41.9	$0.52	98	1.9 s
43	▼ 8	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.32	31	2.1 s
44	▼ 8	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	143	2.5 s
45	▼ 8	Grok 4ClosedxAI	41.5	$6.0	59	12 s
46	▼ 8	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	122	2.3 s
47	▼ 8	GPT-5 mini (high)ClosedOpenAI · 2 more variants	41.2	$0.69	76	111 s
48	▼ 8	Kimi K2 ThinkingOpenKimi	40.9	$1.1	79	2.0 s
49	▼ 8	o3-proClosedOpenAI	40.7	$35	34	111 s
50	▼ 8	Qwen3 Max ThinkingClosedAlibaba · 1 more variant	39.9	$2.4	38	3.8 s
51	▼ 8	MiniMax-M2.1OpenMiniMax	39.4	$0.52	86	2.1 s
52	▼ 8	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	35	1.8 s
53	▼ 8	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	39.0	$30	29	8.8 s
54	▼ 8	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	38.7	$6.0	39	11 s
55	▼ 8	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	193	5.8 s
55	▼ 8	Qwen3.5 Omni PlusClosedAlibaba	38.6	$1.5	52	2.4 s
57	▼ 8	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	38.6	$0.28	135	6.9 s
58	▼ 8	Step 3.5 Flash 2603ClosedStepFun · 1 more variant	38.5	$0.000	150	1.2 s
59	▼ 8	o3ClosedOpenAI	38.4	$3.5	93	9.3 s
60	▼ 8	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	169	2.3 s
61	▼ 8	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	37.1	$2.0	89	19 s
62	▼ 8	MiniMax-M2OpenMiniMax	36.1	$0.52	91	1.9 s
63	▼ 8	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	154	1.3 s
64	▼ 8	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	35.7	$3.4	116	10 s
65	▼ 8	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	35.1	$0.28	222	3.5 s
66	▼ 8	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	34.7	$6.0	—	—
67	▼ 8	Gemini 2.5 ProClosedGoogle	34.6	$3.4	127	21 s
68	▼ 8	Nova 2.0 Lite (high)ClosedAmazon · 3 more variants	34.5	$0.85	130	17 s
69	▼ 8	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$1.9	—	—
70	New	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	68	3.1 s
71	▼ 9	Doubao Seed CodeClosedByteDance Seed	33.5	—	—	—
71	▼ 9	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	329	5.2 s
73	▼ 9	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	211	0.9 s
74	▼ 9	o4-mini (high)ClosedOpenAI	33.1	$1.9	121	24 s
75	▼ 9	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.32	31	2.0 s
76	▼ 9	Mercury 2ClosedInception	32.8	$0.38	717	3.4 s
77	▼ 9	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.96	31	1.6 s
78	▼ 9	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.11	45	1.0 s
79	▼ 9	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
80	▼ 9	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	208	0.6 s
81	▼ 9	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	116	1.1 s
82	▼ 9	Qwen3 MaxClosedAlibaba · 1 more variant	31.4	$2.4	33	3.1 s
83	▼ 9	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
84	▼ 9	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	31.1	—	—	—
85	▼ 9	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.1	18	3.2 s
86	▼ 9	o1ClosedOpenAI · 1 more variant	30.8	$26	89	33 s
87	▼ 9	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	30.3	—	—	—
88	▼ 9	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.2	$0.15	87	1.2 s
89	▼ 9	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$2.6	44	3.1 s
90	▼ 9	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
91	▼ 9	ERNIE 5.0 Thinking PreviewClosedBaidu	29.1	—	—	—
92	▼ 9	Grok Code Fast 1ClosedxAI	28.7	$0.53	152	3.8 s
93	▼ 9	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
94	▼ 9	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	149	1.1 s
95	▼ 9	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.83	—	—
96	▼ 9	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	28.0	$0.85	—	—
97	▼ 9	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.8	$0.26	147	0.8 s
98	▼ 9	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.6	42	3.1 s
99	▼ 9	Magistral Medium 1.2ClosedMistral	27.1	$2.8	66	1.7 s
100	▼ 9	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	174	0.9 s
101	▼ 9	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.1	—	—
102	▼ 9	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	27.0	$0.85	217	16 s
103	▼ 9	GPT-5 nano (high)ClosedOpenAI · 2 more variants	26.8	$0.14	157	91 s
104	▼ 9	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	148	2.2 s
105	▼ 9	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	45	3.2 s
106	▼ 9	GPT-4.1ClosedOpenAI	26.3	$3.5	97	1.0 s
107	New	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	207	1.1 s
108	▼ 10	Qwen3.5 Omni FlashClosedAlibaba	25.9	$0.28	164	2.0 s
108	▼ 10	Solar Pro 3ClosedUpstage	25.9	—	—	—
110	▼ 10	o3-miniClosedOpenAI · 1 more variant	25.9	$1.9	140	8.4 s
111	▼ 10	o1-proClosedOpenAI	25.8	$263	—	—
112	▼ 10	JT-MINIClosedChina Mobile	25.4	—	—	—
113	▼ 10	Grok 3ClosedxAI	25.2	$6.0	76	1.4 s
114	▼ 10	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	36	3.1 s
115	▼ 10	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$1.2	54	2.5 s
116	▼ 10	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$3.0	53	3.2 s
117	▼ 10	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	89	2.6 s
118	▼ 10	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
119	▼ 10	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.10	229	0.7 s
120	▼ 10	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
121	▼ 10	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.096	128	2.4 s
122	▼ 10	LongCat Flash LiteOpenLongCat	23.9	$0.000	113	7.2 s
123	▼ 10	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	25	2.6 s
124	▼ 10	GLM-4.5-AirOpenZ AI	23.2	$0.37	82	3.0 s
125	▼ 10	Mi:dm K 2.5 ProClosedKorea Telecom	23.1	—	—	—
126	▼ 10	GPT-4.1 miniClosedOpenAI	22.9	$0.70	74	0.9 s
127	▼ 10	Mistral Large 3OpenMistral	22.8	$0.75	50	48 s
128	▼ 10	Ring-1TOpenInclusionAI	22.8	—	—	—
129	▼ 10	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.75	144	2.5 s
130	▼ 10	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.2	—	—
131	▼ 10	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
132	▼ 10	Devstral 2OpenMistral	22.0	$0.000	72	1.1 s
133	▼ 10	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
134	▼ 10	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	21.7	$0.18	—	—
135	▼ 10	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
136	▼ 10	Mistral Medium 3.1ClosedMistral	21.3	$0.80	47	1.3 s
137	▼ 10	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
138	▼ 10	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$1.2	51	2.7 s
139	▼ 10	o1-miniClosedOpenAI	20.4	—	—	—
140	▼ 10	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	149	2.3 s
141	▼ 10	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.90	107	2.6 s
142	▼ 10	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
143	▼ 10	QwQ 32BOpenAlibaba	19.7	$0.75	29	2.1 s
144	▼ 10	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.75	111	2.3 s
145	▼ 10	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	19.6	—	—	—
146	▼ 10	Devstral Small 2OpenMistral	19.5	$0.000	62	1.2 s
147	▼ 10	Motif-2-12.7B-ReasoningClosedMotif Technologies	19.1	—	—	—
148	▼ 10	Ling-1TOpenInclusionAI	19.0	—	—	—
149	▼ 10	Nova PremierClosedAmazon	19.0	$5.0	26	3.2 s
150	▼ 10	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage · 3 more variants	18.8	—	—	—
151	▼ 10	Magistral Medium 1ClosedMistral	18.8	—	—	—
152	▼ 10	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
152	▼ 10	Mistral Medium 3ClosedMistral	18.8	$0.80	64	1.3 s
154	▼ 10	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	49	1.7 s
155	▼ 10	Claude 3.5 HaikuClosedAnthropic	18.7	$1.6	—	—
155	▼ 10	Devstral MediumClosedMistral	18.7	$0.80	133	1.2 s
157	▼ 10	GPT-4o (Aug '24)ClosedOpenAI · 4 more variants	18.6	$4.4	63	1.4 s
158	▼ 10	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	18.5	$0.26	—	—
159	▼ 10	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
160	▼ 10	Llama 4 MaverickOpenMeta	18.4	$0.48	113	1.0 s
161	▼ 10	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
162	▼ 10	Magistral Small 1.2OpenMistral	18.2	$0.75	143	0.8 s
162	▼ 10	Sarvam 105B (high)OpenSarvam	18.2	$0.000	121	2.4 s
164	▼ 10	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
165	▼ 10	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	—	—	—
166	▼ 10	Claude 3 OpusClosedAnthropic	18.0	$30	—	—
167	▼ 10	Sonar ReasoningClosedPerplexity	17.9	—	—	—
168	▼ 10	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	17.6	$0.18	305	19 s
169	▼ 10	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	29	2.4 s
170	▼ 10	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	75	2.6 s
171	▼ 10	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
172	▼ 10	Magistral Small 1OpenMistral	16.8	—	—	—
173	▼ 10	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
174	▼ 10	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	110	2.5 s
175	▼ 10	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$2.6	89	2.5 s
176	▼ 10	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
177	▼ 10	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	—	—
178	▼ 10	Qwen2.5 MaxClosedAlibaba	16.3	$2.8	46	3.3 s
179	▼ 10	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$1.3	62	2.8 s
180	▼ 10	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
181	▼ 10	Qwen3 VL 30B A3B InstructOpenAlibaba	16.1	$0.35	111	2.2 s
182	▼ 10	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	16.0	—	—	—
183	▼ 10	Ministral 3 14BOpenMistral	16.0	$0.20	99	0.6 s
184	▼ 10	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	44	1.8 s
185	▼ 10	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	15.9	$6.0	—	—
186	▼ 10	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
187	▼ 10	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
188	▼ 10	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	92	2.3 s
189	▼ 10	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	80	2.0 s
190	▼ 10	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.000	28	3.7 s
191	▼ 10	SonarClosedPerplexity	15.5	—	—	—
192	▼ 10	Step3 VL 10BOpenStepFun	15.5	—	—	—
193	▼ 10	Sonar ProClosedPerplexity	15.2	—	—	—
194	▼ 10	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
195	▼ 10	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
196	▼ 10	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	34	1.8 s
196	▼ 10	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	39	1.7 s
198	▼ 10	Mistral Small 3.2OpenMistral	15.1	$0.15	118	0.6 s
199	▼ 10	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	42	2.6 s
200	▼ 10	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.35	55	2.2 s
201	▼ 10	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	26	3.7 s
202	▼ 10	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	125	0.7 s
203	▼ 10	Ministral 3 8BOpenMistral	14.8	$0.15	176	0.6 s
204	▼ 10	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	118	0.7 s
205	▼ 10	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	14.7	—	—	—
206	▼ 10	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
207	▼ 10	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	91	1.4 s
208	▼ 10	Mistral Small 3.1OpenMistral	14.5	$0.15	128	0.7 s
209	▼ 10	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
210	▼ 10	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
211	▼ 10	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	120	2.4 s
212	▼ 10	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	86	2.3 s
213	▼ 10	Pixtral LargeOpenMistral	14.0	$3.0	50	1.6 s
214	▼ 10	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
215	▼ 10	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	13.8	—	—	—
216	▼ 10	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
217	▼ 10	GPT-4 TurboClosedOpenAI	13.7	$15	28	2.8 s
218	▼ 10	Llama 4 ScoutOpenMeta	13.5	$0.29	139	0.8 s
219	▼ 10	Command AOpenCohere	13.5	$4.4	37	2.4 s
219	▼ 10	Nova ProClosedAmazon	13.5	$1.4	—	—
221	▼ 10	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	39	1.7 s
222	▼ 10	Grok BetaClosedxAI	13.3	—	—	—
223	▼ 10	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
224	▼ 10	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.66	84	2.3 s
225	▼ 10	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	165	0.7 s
226	▼ 10	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
227	▼ 10	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
228	▼ 10	GPT-4ClosedOpenAI	12.8	$38	—	—
229	▼ 10	Mistral Small 3OpenMistral	12.7	$0.15	132	0.8 s
230	▼ 10	Nova LiteClosedAmazon	12.7	$0.11	165	1.0 s
231	▼ 10	GPT-4o miniClosedOpenAI	12.6	$0.26	54	1.2 s
232	▼ 10	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
233	▼ 10	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	15	2.1 s
234	▼ 10	Sarvam 30B (high)OpenSarvam	12.3	$0.000	186	2.0 s
235	▼ 10	Claude 3 HaikuClosedAnthropic	12.3	$0.50	—	—
236	▼ 10	Mistral SabaClosedMistral	12.1	—	—	—
237	▼ 10	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
238	▼ 10	R1 1776OpenPerplexity	12.0	—	—	—
239	▼ 10	Qwen2.5 TurboClosedAlibaba	12.0	$0.088	63	2.4 s
240	▼ 10	Reka Flash (Sep '24)ClosedReka AI	12.0	$0.35	58	2.0 s
241	▼ 10	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	55	1.2 s
241	▼ 10	Solar MiniOpenUpstage	11.9	$0.15	—	—
243	▼ 10	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	142	0.9 s
244	▼ 10	Grok-1OpenxAI	11.7	—	—	—
245	▼ 10	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
246	▼ 10	Ministral 3 3BOpenMistral	11.2	$0.10	279	0.4 s
247	▼ 10	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
248	▼ 10	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	62	1.5 s
249	▼ 10	Granite 4.0 H SmallOpenIBM	10.8	$0.11	430	10 s
250	▼ 10	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
251	▼ 10	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	95	1.9 s
252	▼ 10	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
253	▼ 10	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	62	1.4 s
254	▼ 10	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	—	—
255	▼ 10	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	122	0.5 s
256	▼ 10	Phi-4OpenMicrosoft Azure	10.4	$0.22	27	2.2 s
257	▼ 10	Gemma 3 27B InstructOpenGoogle	10.3	$0.000	28	2.0 s
258	▼ 10	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
259	▼ 10	Nova MicroClosedAmazon	10.3	$0.061	301	0.9 s
260	▼ 10	Mistral Small (Sep '24)OpenMistral · 1 more variant	10.2	$0.30	132	0.7 s
261	▼ 10	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
262	▼ 10	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	10.1	—	—	—
263	▼ 10	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
264	▼ 10	Phi-4 Multimodal InstructOpenMicrosoft Azure	10.0	$0.000	17	0.8 s
265	▼ 10	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
266	▼ 10	Mistral Large (Feb '24)ClosedMistral	9.9	$6.0	—	—
267	▼ 10	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
268	▼ 10	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
269	▼ 10	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	51	1.1 s
270	▼ 10	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
271	▼ 10	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
272	▼ 10	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
273	▼ 10	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
274	▼ 10	Claude 2.1ClosedAnthropic	9.3	—	—	—
275	▼ 10	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
276	▼ 10	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
277	▼ 10	Claude 2.0ClosedAnthropic	9.1	—	—	—
277	▼ 10	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
279	▼ 10	Mistral MediumClosedMistral	9.0	$4.1	41	1.4 s
280	▼ 10	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
281	▼ 10	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
282	▼ 10	Arctic InstructOpenSnowflake	8.8	—	—	—
282	▼ 10	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
284	▼ 10	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	27	3.3 s
285	▼ 10	LFM 40BClosedLiquid AI	8.8	—	—	—
286	▼ 10	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	50	0.7 s
287	▼ 10	PALM-2ClosedGoogle	8.6	—	—	—
288	▼ 10	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
289	▼ 10	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
290	▼ 10	Phi-4 Mini InstructOpenMicrosoft Azure	8.4	$0.000	44	0.8 s
290	▼ 10	Sarvam M (Reasoning)OpenSarvam	8.4	—	—	—
292	▼ 10	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
292	▼ 10	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
294	▼ 10	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
295	▼ 10	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
296	▼ 10	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
297	▼ 10	DBRX InstructOpenDatabricks	8.3	—	—	—
298	▼ 10	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
299	▼ 10	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
300	▼ 10	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
301	▼ 10	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
301	▼ 10	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
303	▼ 10	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
304	▼ 10	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
305	▼ 10	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	128	1.8 s
306	▼ 10	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	181	0.9 s
307	▼ 10	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
308	▼ 10	Gemma 3 270MOpenGoogle	7.7	—	—	—
309	▼ 10	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
310	▼ 10	Granite 4.0 MicroOpenIBM	7.7	—	—	—
311	▼ 10	Claude InstantClosedAnthropic	7.4	—	—	—
311	▼ 10	Llama 65BOpenMeta	7.4	—	—	—
311	▼ 10	Mistral 7B InstructOpenMistral	7.4	$0.25	165	0.6 s
311	▼ 10	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
315	▼ 10	Granite 4.0 1BOpenIBM	7.3	—	—	—
316	▼ 10	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
317	▼ 10	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	356	26 s
318	▼ 10	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	163	1.6 s
319	▼ 10	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	29	1.3 s
319	▼ 10	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
321	▼ 10	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
322	▼ 10	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	29	1.6 s
323	▼ 10	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	90	0.9 s
324	▼ 10	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
325	▼ 10	Granite 4.0 350MOpenIBM	6.1	—	—	—
326	▼ 10	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
327	▼ 10	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	49	0.9 s
328	▼ 10	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
329	▼ 10	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
330	▼ 10	Tiny Aya GlobalOpenCohere	4.7	—	—	—

280 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