Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Gemini 3.1 Pro PreviewClosedGoogle	57.2	$4.5	115	32 s
2	—	GPT-5.4 (xhigh)ClosedOpenAI · 1 more variant	56.8	$5.6	83	196 s
3	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	53.6	$4.8	68	96 s
4	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	53.0	$10	44	19 s
5	New	Muse SparkClosedMeta	52.2	—	—	—
6	▼ 1	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	51.7	$6.0	63	93 s
7	New	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	66	1.7 s
8	▼ 2	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	51.3	$4.8	69	113 s
9	New	Qwen3.6 PlusClosedAlibaba	50.0	$1.1	50	2.3 s
10	▼ 3	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	73	1.7 s
11	▼ 3	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	49.7	$10	48	16 s
12	▼ 3	MiniMax-M2.7ClosedMiniMax	49.6	$0.52	42	3.2 s
13	New	Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant	49.3	$3.0	194	11 s
14	▼ 4	MiMo-V2-ProClosedXiaomi	49.2	$1.5	69	2.8 s
15	▼ 4	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	89	111 s
16	▼ 2	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	48.9	$1.7	166	7.6 s
17	New	Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant	48.5	$3.0	198	11 s
18	▼ 5	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	48.4	$4.5	126	33 s
19	▼ 4	GPT-5.1 (high)ClosedOpenAI · 1 more variant	47.7	$3.4	89	44 s
20	▼ 4	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.2	37	2.1 s
21	▼ 4	GLM-5-TurboClosedZ AI	46.8	—	—	—
22	▼ 4	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	46.4	$1.1	153	8.0 s
23	▼ 4	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.1	$1.4	80	2.5 s
24	▼ 1	MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant	44.9	—	—	—
25	▼ 5	GPT-5 (high)ClosedOpenAI · 4 more variants	44.6	$3.4	80	80 s
25	▼ 5	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	183	8.6 s
27	▼ 5	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	44.0	$0.46	188	4.5 s
28	▼ 4	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	162	6.0 s
29	▼ 4	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	43.0	$6.0	44	13 s
30	New	GLM 5V Turbo (Reasoning)ClosedZ AI	42.9	—	—	—
31	▼ 5	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	69	1.4 s
32	▼ 5	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	87	5.7 s
33	▼ 5	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	42.0	$30	33	14 s
34	▼ 5	MiniMax-M2.5OpenMiniMax	41.9	$0.52	69	2.5 s
35	▼ 5	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.32	46	2.1 s
36	▼ 5	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	122	2.4 s
37	▼ 5	Grok 4ClosedxAI	41.5	$6.0	58	12 s
38	▼ 5	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	130	2.2 s
39	▼ 5	GPT-5 mini (high)ClosedOpenAI · 2 more variants	41.2	$0.69	75	87 s
40	▼ 5	Kimi K2 ThinkingOpenKimi	40.9	$1.1	76	1.6 s
41	▼ 5	o3-proClosedOpenAI	40.7	$35	29	101 s
42	▼ 5	Qwen3 Max ThinkingClosedAlibaba · 1 more variant	39.9	$2.4	37	4.0 s
43	▼ 5	MiniMax-M2.1OpenMiniMax	39.4	$0.52	69	2.2 s
44	New	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	36	1.7 s
45	▼ 6	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	39.0	$30	32	11 s
46	▼ 6	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	38.7	$6.0	44	14 s
47	▼ 6	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	185	7.1 s
47	New	Qwen3.5 Omni PlusClosedAlibaba	38.6	$1.5	48	2.5 s
49	▼ 7	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	38.6	$0.28	119	7.0 s
50	▼ 7	o3ClosedOpenAI	38.4	$3.5	88	11 s
51	▼ 7	Step 3.5 FlashOpenStepFun	37.8	$0.15	165	2.3 s
52	▼ 7	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	185	2.1 s
53	▼ 7	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	37.1	$2.0	99	15 s
54	▼ 7	MiniMax-M2OpenMiniMax	36.1	$0.52	70	2.0 s
55	▼ 7	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	172	1.0 s
56	▼ 7	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	35.7	$3.4	126	12 s
57	▼ 7	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	35.1	$0.28	164	3.6 s
58	▼ 7	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	34.7	$6.0	—	—
59	▼ 7	Gemini 2.5 ProClosedGoogle	34.6	$3.4	117	29 s
60	▲ 10	Nova 2.0 Lite (high)ClosedAmazon · 3 more variants	34.5	$0.85	157	12 s
61	▼ 8	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$0.80	—	—
62	▼ 8	Doubao Seed CodeClosedByteDance Seed	33.5	—	—	—
62	▼ 8	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	189	9.0 s
64	▼ 8	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	215	0.9 s
65	▼ 8	o4-mini (high)ClosedOpenAI	33.1	$1.9	125	26 s
66	▼ 8	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.32	45	2.2 s
67	▼ 8	Mercury 2ClosedInception	32.8	$0.38	843	3.7 s
68	▼ 8	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.98	64	1.2 s
69	▼ 8	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.096	105	0.7 s
70	▼ 8	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
71	▼ 8	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	189	0.6 s
72	New	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	101	1.0 s
73	▼ 9	Qwen3 MaxClosedAlibaba · 1 more variant	31.4	$2.4	61	2.8 s
74	New	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
75	▼ 10	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	31.1	—	—	—
76	▼ 10	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.2	50	1.1 s
77	▼ 10	o1ClosedOpenAI · 1 more variant	30.8	$26	91	33 s
78	▼ 10	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	30.3	—	—	—
79	▼ 10	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.2	$0.15	80	1.6 s
80	▼ 9	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$2.6	38	3.1 s
81	▼ 9	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
82	▼ 9	ERNIE 5.0 Thinking PreviewClosedBaidu	29.1	—	—	—
83	▼ 9	Grok Code Fast 1ClosedxAI	28.7	$0.53	138	3.8 s
84	▼ 9	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	145	1.9 s
85	▼ 9	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.84	—	—
86	▼ 9	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	28.0	$0.85	—	—
87	▼ 9	Nemotron Cascade 2 30B A3BOpenNVIDIA	27.7	—	—	—
88	▼ 9	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.6	55	2.9 s
89	▼ 9	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.2	$0.26	144	3.4 s
90	▼ 9	Magistral Medium 1.2ClosedMistral	27.1	$2.8	86	1.7 s
91	▼ 9	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	190	0.7 s
92	▼ 9	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.4	—	—
93	▼ 9	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	27.0	$0.85	199	22 s
94	▼ 9	GPT-5 nano (high)ClosedOpenAI · 2 more variants	26.8	$0.14	134	104 s
95	▼ 9	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	172	2.2 s
96	▼ 9	GLM-4.5 (Reasoning)OpenZ AI	26.4	$0.84	48	2.9 s
97	▼ 9	GPT-4.1ClosedOpenAI	26.3	$3.5	94	1.1 s
98	New	Qwen3.5 Omni FlashClosedAlibaba	25.9	$0.28	164	1.9 s
98	New	Solar Pro 3ClosedUpstage	25.9	—	—	—
100	▼ 11	o3-miniClosedOpenAI · 1 more variant	25.9	$1.9	140	8.3 s
101	▼ 11	o1-proClosedOpenAI	25.8	$263	—	—
102	▼ 11	Grok 3ClosedxAI	25.2	$6.0	53	1.4 s
103	▼ 11	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	36	3.1 s
104	▼ 11	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$1.2	55	2.4 s
105	▼ 11	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$3.0	57	3.0 s
106	▼ 11	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	90	2.8 s
107	▼ 11	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
108	▼ 11	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.095	249	0.7 s
109	▼ 11	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
110	▼ 11	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.11	101	1.7 s
111	▼ 11	LongCat Flash LiteOpenLongCat	23.9	$0.000	117	6.7 s
112	▼ 11	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	26	2.3 s
113	▼ 11	GLM-4.5-AirOpenZ AI	23.2	$0.43	83	1.3 s
114	▼ 11	Mi:dm K 2.5 ProClosedKorea Telecom	23.1	—	—	—
115	▼ 11	GPT-4.1 miniClosedOpenAI	22.9	$0.70	74	0.9 s
116	▼ 11	Mistral Large 3OpenMistral	22.8	$0.75	38	1.7 s
117	▼ 11	Ring-1TOpenInclusionAI	22.8	—	—	—
118	▼ 11	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.75	150	2.5 s
119	▼ 11	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.3	—	—
120	▼ 11	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
121	▼ 11	Devstral 2OpenMistral	22.0	$0.000	71	0.9 s
122	▼ 11	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
123	▼ 11	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	21.7	$0.18	—	—
124	▼ 11	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
125	▼ 11	Mistral Medium 3.1ClosedMistral	21.3	$0.80	100	1.4 s
126	▼ 11	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
127	▼ 11	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$1.2	56	2.8 s
128	▼ 11	o1-miniClosedOpenAI	20.4	—	—	—
129	▼ 11	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	162	2.2 s
130	▼ 11	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.90	28	2.8 s
131	▼ 11	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
132	▼ 11	QwQ 32BOpenAlibaba	19.7	$0.75	31	2.1 s
133	▼ 11	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.75	111	2.2 s
134	▼ 11	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	19.6	—	—	—
135	▼ 11	Devstral Small 2OpenMistral	19.5	$0.000	72	1.0 s
136	▼ 11	Motif-2-12.7B-ReasoningClosedMotif Technologies	19.1	—	—	—
137	▼ 11	Ling-1TOpenInclusionAI	19.0	—	—	—
138	▼ 11	Nova PremierClosedAmazon	19.0	$5.0	26	3.0 s
139	▼ 11	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage · 3 more variants	18.8	—	—	—
140	▼ 11	Magistral Medium 1ClosedMistral	18.8	—	—	—
141	New	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
141	▼ 11	Mistral Medium 3ClosedMistral	18.8	$0.80	52	1.3 s
143	▼ 12	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	55	1.5 s
144	▼ 12	Claude 3.5 HaikuClosedAnthropic	18.7	$1.6	—	—
144	▼ 12	Devstral MediumClosedMistral	18.7	$0.80	131	1.3 s
146	▼ 12	GPT-4o (Aug '24)ClosedOpenAI · 4 more variants	18.6	$4.4	88	1.1 s
147	▼ 12	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	18.5	$0.26	—	—
148	▼ 12	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
149	▼ 12	Llama 4 MaverickOpenMeta	18.4	$0.46	110	1.0 s
150	▼ 12	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
151	▼ 12	Magistral Small 1.2OpenMistral	18.2	$0.75	162	0.8 s
151	▼ 12	Sarvam 105B (high)OpenSarvam	18.2	$0.000	112	2.5 s
153	▼ 12	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
154	▼ 12	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	$0.075	—	—
155	▼ 12	Claude 3 OpusClosedAnthropic	18.0	$30	—	—
156	▼ 12	Sonar ReasoningClosedPerplexity	17.9	—	—	—
157	▼ 12	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	17.6	$0.18	325	20 s
158	▼ 12	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	29	2.4 s
159	▼ 12	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	73	2.6 s
160	▼ 12	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	$0.27	44	1.4 s
161	▼ 12	Magistral Small 1OpenMistral	16.8	—	—	—
162	▼ 12	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
163	▼ 12	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	115	2.4 s
164	▼ 12	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$2.6	98	2.4 s
165	▼ 12	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
166	▼ 12	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	—	—
167	▼ 12	Qwen2.5 MaxClosedAlibaba	16.3	$2.8	45	3.3 s
168	▼ 12	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$1.3	61	2.6 s
169	▼ 12	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
170	▼ 12	Qwen3 VL 30B A3B InstructOpenAlibaba	16.1	$0.35	111	2.2 s
171	▼ 12	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	16.0	—	—	—
172	▼ 12	Ministral 3 14BOpenMistral	16.0	$0.20	108	0.7 s
173	▼ 12	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	39	3.0 s
174	▼ 12	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	15.9	$6.0	—	—
175	▼ 12	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
176	▼ 12	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
177	▼ 12	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	62	2.4 s
178	▼ 12	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	91	1.9 s
179	▼ 12	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.000	28	3.5 s
180	▼ 12	SonarClosedPerplexity	15.5	—	—	—
181	▼ 12	Step3 VL 10BOpenStepFun	15.5	—	—	—
182	▼ 12	Sonar ProClosedPerplexity	15.2	—	—	—
183	New	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
184	▼ 13	QwQ 32B-PreviewOpenAlibaba	15.2	$0.14	45	1.1 s
185	▼ 13	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	50	1.9 s
185	▼ 13	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	39	1.6 s
187	▼ 13	Mistral Small 3.2OpenMistral	15.1	$0.15	121	0.8 s
188	▼ 13	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.5 s
189	▼ 13	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.35	85	2.0 s
190	▼ 13	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	25	3.5 s
191	▼ 13	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	142	0.6 s
192	▼ 13	Ministral 3 8BOpenMistral	14.8	$0.15	180	0.6 s
193	▼ 13	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	157	0.6 s
194	▼ 13	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	14.7	—	—	—
195	▼ 13	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
196	▼ 13	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.61	87	1.4 s
197	▼ 13	Mistral Small 3.1OpenMistral	14.5	$0.15	125	1.6 s
198	▼ 13	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
199	▼ 13	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
200	▼ 13	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	121	2.3 s
201	▼ 13	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	85	2.6 s
202	▼ 13	Pixtral LargeOpenMistral	14.0	$3.0	52	1.5 s
203	▼ 13	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
204	▼ 13	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	13.8	—	—	—
205	▼ 13	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
206	▼ 13	GPT-4 TurboClosedOpenAI	13.7	$15	22	2.5 s
207	▼ 13	Llama 4 ScoutOpenMeta	13.5	$0.29	143	0.8 s
208	▼ 13	Command AOpenCohere	13.5	$4.4	32	2.1 s
208	▼ 13	Nova ProClosedAmazon	13.5	$1.4	—	—
210	▼ 13	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	46	1.9 s
211	▼ 13	Grok BetaClosedxAI	13.3	—	—	—
212	▼ 13	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
213	▼ 13	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.66	78	2.2 s
214	▼ 13	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	154	0.7 s
215	▼ 13	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
216	▼ 13	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
217	▼ 13	GPT-4ClosedOpenAI	12.8	$38	—	—
218	▼ 13	Mistral Small 3OpenMistral	12.7	$0.15	123	1.5 s
219	▼ 13	Nova LiteClosedAmazon	12.7	$0.11	150	0.9 s
220	▼ 13	GPT-4o miniClosedOpenAI	12.6	$0.26	38	2.6 s
221	▼ 13	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
222	▼ 13	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	27	2.1 s
223	▼ 13	Sarvam 30B (high)OpenSarvam	12.3	$0.000	142	1.9 s
224	▼ 13	Claude 3 HaikuClosedAnthropic	12.3	$0.50	132	1.2 s
225	▼ 13	Mistral SabaClosedMistral	12.1	—	—	—
226	▼ 13	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
227	▼ 13	R1 1776OpenPerplexity	12.0	—	—	—
228	▼ 13	Qwen2.5 TurboClosedAlibaba	12.0	$0.088	64	2.4 s
229	▼ 13	Reka Flash (Sep '24)ClosedReka AI	12.0	$0.35	58	2.0 s
230	▼ 13	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$0.72	54	1.1 s
230	▼ 13	Solar MiniOpenUpstage	11.9	$0.15	—	—
232	▼ 13	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	150	0.8 s
233	▼ 13	Grok-1OpenxAI	11.7	—	—	—
234	▼ 13	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
235	▼ 13	Ministral 3 3BOpenMistral	11.2	$0.10	279	0.5 s
236	▼ 13	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
237	▼ 13	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	59	1.4 s
238	▼ 13	Granite 4.0 H SmallOpenIBM	10.8	$0.11	442	10 s
239	▼ 13	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
240	▼ 13	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	95	1.9 s
241	▼ 13	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
242	▼ 13	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	59	1.4 s
243	▼ 13	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	—	—
244	▼ 13	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	52	0.5 s
245	▼ 13	Phi-4OpenMicrosoft Azure	10.4	$0.22	34	2.1 s
246	▼ 13	Gemma 3 27B InstructOpenGoogle	10.3	$0.000	28	2.7 s
247	▼ 13	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
248	▼ 13	Nova MicroClosedAmazon	10.3	$0.061	285	0.8 s
249	▼ 13	Mistral Small (Sep '24)OpenMistral · 1 more variant	10.2	$0.30	121	2.4 s
250	▼ 13	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
251	▼ 13	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	10.1	—	—	—
252	▼ 13	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
253	▼ 13	Phi-4 Multimodal InstructOpenMicrosoft Azure	10.0	$0.000	17	0.8 s
254	▼ 13	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
255	▼ 13	Mistral Large (Feb '24)ClosedMistral	9.9	$6.0	—	—
256	▼ 13	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
257	▼ 13	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
258	▼ 13	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.085	51	0.9 s
259	▼ 13	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
260	▼ 13	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
261	▼ 13	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
262	▼ 13	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
263	▼ 13	Claude 2.1ClosedAnthropic	9.3	—	—	—
264	▼ 13	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
265	▼ 13	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
266	▼ 13	Claude 2.0ClosedAnthropic	9.1	—	—	—
266	▼ 13	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
268	▼ 13	Mistral MediumClosedMistral	9.0	$4.1	99	1.3 s
269	▼ 13	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
270	▼ 13	Llama 3 Instruct 70BOpenMeta	8.9	$0.87	—	—
271	▼ 13	Arctic InstructOpenSnowflake	8.8	—	—	—
271	▼ 13	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
273	▼ 13	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	29	35 s
274	▼ 13	LFM 40BClosedLiquid AI	8.8	—	—	—
275	▼ 13	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.16	52	0.8 s
276	▼ 13	PALM-2ClosedGoogle	8.6	—	—	—
277	▼ 13	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
278	▼ 13	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
279	▼ 13	Phi-4 Mini InstructOpenMicrosoft Azure	8.4	$0.000	43	0.8 s
279	▼ 13	Sarvam M (Reasoning)OpenSarvam	8.4	—	—	—
281	▼ 13	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
281	▼ 13	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
283	▼ 13	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
284	▼ 13	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
285	▼ 13	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
286	▼ 13	DBRX InstructOpenDatabricks	8.3	—	—	—
287	▼ 13	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
288	▼ 13	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
289	▼ 13	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
290	▼ 13	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
290	▼ 13	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
292	▼ 13	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
293	▼ 13	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
294	▼ 13	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	124	1.7 s
295	▼ 13	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	174	0.9 s
296	▼ 13	Mixtral 8x7B InstructOpenMistral	7.7	$0.56	—	—
297	▼ 13	Gemma 3 270MOpenGoogle	7.7	—	—	—
298	▼ 13	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
299	▼ 13	Granite 4.0 MicroOpenIBM	7.7	—	—	—
300	▼ 13	Claude InstantClosedAnthropic	7.4	—	—	—
300	▼ 13	Llama 65BOpenMeta	7.4	—	—	—
300	▼ 13	Mistral 7B InstructOpenMistral	7.4	$0.25	180	0.6 s
300	▼ 13	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
304	▼ 13	Granite 4.0 1BOpenIBM	7.3	—	—	—
305	▼ 13	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
306	▼ 13	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	321	21 s
307	▼ 13	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	159	1.6 s
308	▼ 13	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	38	1.1 s
308	▼ 13	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
310	▼ 13	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
311	▼ 13	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	30	1.6 s
312	▼ 13	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	88	1.0 s
313	▼ 13	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
314	▼ 13	Granite 4.0 350MOpenIBM	6.1	—	—	—
315	▼ 13	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
316	▼ 13	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	37	0.8 s
317	▼ 13	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
318	▼ 13	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
319	▼ 13	Tiny Aya GlobalOpenCohere	4.7	—	—	—

269 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