Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic	59.9	$20	—	—
2	—	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic	55.7	$10	59	21 s
3	—	GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants	54.8	$11	56	84 s
4	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	53.5	$10	53	18 s
5	▲ 1	GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants	51.4	$5.6	146	115 s
6	New	GLM-5.2 (max)OpenZ AI	51.1	$2.2	99	2.1 s
7	▲ 1	Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants	50.2	$3.4	161	18 s
8	▲ 10	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	47.2	$6.0	57	106 s
9	▼ 4	Gemini 3.1 Pro PreviewClosedGoogle	46.5	$4.5	123	19 s
10	▼ 3	Qwen3.7 MaxClosedAlibaba	46.0	$3.8	109	2.7 s
11	▼ 2	MiniMax-M3OpenMiniMax	44.4	$0.52	60	2.7 s
12	▲ 7	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	44.3	$0.54	75	1.8 s
13	▼ 1	GPT-5.3 Codex (xhigh)ClosedOpenAI	44.3	$4.8	72	87 s
14	▲ 1	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	43.7	$10	44	20 s
15	▲ 1	Muse SparkClosedMeta	43.1	—	—	—
16	▼ 6	Kimi K2.6OpenKimi · 1 more variant	42.8	$1.7	44	2.5 s
17	▼ 6	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.2	$0.54	50	2.6 s
18	▲ 3	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	42.2	$4.8	70	133 s
19	New	Kimi K2.7 CodeOpenKimi	41.9	$1.7	56	2.3 s
20	▲ 4	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	40.8	$10	55	14 s
21	▲ 6	MiMo-V2-ProClosedXiaomi	40.3	$1.5	51	2.6 s
22	▲ 15	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	40.3	$0.18	107	1.3 s
23	▼ 3	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	40.2	$2.2	79	1.5 s
24	▲ 4	GPT-5.2 Codex (xhigh)ClosedOpenAI	40.1	$4.8	138	38 s
25	▲ 4	MiMo-V2.5OpenXiaomi	40.1	$0.18	78	2.5 s
26	▼ 9	Qwen3.6 Max PreviewClosedAlibaba	40.0	$2.9	42	3.4 s
27	▲ 3	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	40.0	$1.7	175	8.6 s
28	▼ 6	Qwen3.6 PlusClosedAlibaba	39.6	$1.1	50	2.7 s
29	▲ 3	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	39.6	$4.5	—	—
30	▼ 7	GLM-5 (Reasoning)OpenZ AI · 1 more variant	39.5	$1.6	75	1.7 s
31	▼ 18	Qwen3.7 PlusClosedAlibaba	39.0	$0.59	51	2.6 s
32	▲ 1	GPT-5.1 (high)ClosedOpenAI · 1 more variant	38.9	$3.4	93	43 s
33	▲ 11	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	38.2	$0.46	157	5.0 s
34	▼ 9	MiniMax-M2.7OpenMiniMax	38.1	$0.52	44	2.1 s
35	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	38.1	$1.2	55	3.0 s
36	—	GLM-5-TurboClosedZ AI	38.1	—	—	—
37	▼ 3	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	170	1.1 s
38	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	37.8	$1.1	166	6.9 s
39	▼ 25	Grok 4.3 (high)ClosedxAI · 3 more variants	37.6	$1.6	152	11 s
40	▼ 1	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.1	$1.4	55	3.8 s
41	▼ 15	Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant	37.0	$3.0	148	13 s
42	▼ 11	Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant	36.5	$3.0	156	13 s
43	▼ 2	MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant	36.4	$0.80	75	3.0 s
44	▼ 2	GPT-5 Codex (high)ClosedOpenAI	36.1	$3.4	166	16 s
45	▼ 2	GPT-5 (high)ClosedOpenAI · 4 more variants	36.1	$3.4	92	83 s
46	—	GPT-5.1 Codex (high)ClosedOpenAI	34.7	$3.4	171	7.7 s
47	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	34.7	$6.0	50	15 s
48	—	GLM 5V Turbo (Reasoning)ClosedZ AI	34.5	—	—	—
49	▲ 1	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	33.8	$1.0	115	1.0 s
50	▲ 1	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	33.8	$0.83	80	5.7 s
51	▲ 1	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	33.7	$30	34	15 s
52	▼ 12	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	33.7	$1.4	51	2.7 s
53	—	MiniMax-M2.5OpenMiniMax	33.7	$0.52	203	7.3 s
54	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	33.6	$0.20	117	4.1 s
55	—	GPT-5.5 Instant (May 2026)ClosedOpenAI	33.5	$11	—	—
56	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	33.4	$0.34	—	—
57	▲ 1	Grok 4ClosedxAI	33.3	$11	—	—
58	▲ 1	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	33.2	$0.15	96	2.4 s
59	▲ 1	GPT-5 mini (high)ClosedOpenAI · 2 more variants	33.0	$0.69	96	82 s
60	▲ 1	Kimi K2 ThinkingOpenKimi	32.7	$1.1	123	1.5 s
61	▲ 1	o3-proClosedOpenAI	32.5	$35	35	63 s
62	▼ 5	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.3	$1.1	134	2.5 s
63	—	Qwen3 Max ThinkingClosedAlibaba · 1 more variant	31.7	$2.4	—	—
64	▼ 19	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	31.6	$0.56	171	2.5 s
65	▼ 1	MiniMax-M2.1OpenMiniMax	31.4	$0.52	212	9.2 s
66	▲ 1	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	31.0	$30	—	—
67	▲ 1	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	30.7	$6.0	—	—
68	▲ 1	Qwen3.5 Omni PlusClosedAlibaba	30.6	$1.5	52	2.5 s
69	▲ 1	GPT-5.1 Codex mini (high)ClosedOpenAI	30.6	$0.69	212	7.1 s
70	▲ 1	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	30.6	—	—	—
71	▲ 2	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	132	3.4 s
72	▲ 2	o3ClosedOpenAI	30.4	$3.5	127	7.9 s
73	▼ 8	Mistral Medium 3.5OpenMistral	29.9	$3.0	128	2.3 s
74	▼ 25	Step 3.7 FlashOpenStepFun	29.7	$0.44	377	1.0 s
75	▲ 2	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	29.6	$2.0	108	11 s
76	▼ 10	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	29.4	$0.000	34	1.1 s
77	▼ 2	Command A+OpenCohere · 1 more variant	29.3	$0.000	200	0.4 s
78	▼ 2	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.3	$0.69	155	2.2 s
79	▼ 1	JT-35B-FlashClosedChina Mobile	28.4	—	—	—
80	▼ 1	MiniMax-M2OpenMiniMax	28.3	$0.52	112	1.8 s
81	▲ 1	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	27.4	$0.28	—	—
82	▲ 1	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	27.1	—	—	—
83	▲ 1	Gemini 2.5 ProClosedGoogle	27.0	$3.4	129	17 s
84	▲ 2	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	26.3	$1.9	—	—
85	▲ 2	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
86	▼ 14	Step 3.5 Flash 2603ClosedStepFun · 1 more variant	26.0	$0.15	208	1.2 s
87	▲ 1	Doubao Seed CodeClosedByteDance Seed	26.0	—	—	—
88	▲ 12	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	25.7	$0.20	—	—
89	▲ 2	o4-mini (high)ClosedOpenAI	25.6	$1.9	170	17 s
90	▲ 2	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.4	$0.31	—	—
91	▼ 11	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.41	148	1.4 s
92	▲ 1	Mercury 2ClosedInception	25.3	$0.38	924	4.6 s
93	▲ 1	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	25.1	$0.96	46	2.6 s
94	▼ 5	Gemini 3.1 Flash-LiteClosedGoogle	25.0	$0.56	284	5.4 s
95	—	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	25.0	$0.11	63	2.0 s
96	—	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	24.7	—	—	—
97	▲ 1	Trinity Large ThinkingOpenArcee AI	24.5	$0.40	158	1.1 s
98	▲ 1	Qwen3 MaxClosedAlibaba · 1 more variant	24.0	$3.0	59	2.4 s
99	▼ 9	gpt-oss-120b (high)OpenOpenAI · 1 more variant	23.8	$0.26	341	1.0 s
100	▲ 1	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	23.8	—	—	—
101	▲ 1	Kimi K2 0905OpenKimi · 1 more variant	23.5	$1.1	27	2.4 s
102	▲ 1	o1ClosedOpenAI · 1 more variant	23.4	$26	100	25 s
103	▲ 1	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	23.0	—	—	—
104	▲ 1	EXAONE 4.5 33BOpenLG AI Research	23.0	—	—	—
105	▲ 1	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	22.9	$0.15	87	1.5 s
106	▼ 9	Grok 3 mini Reasoning (high)ClosedxAI	22.5	$0.35	82	0.7 s
107	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.3	$0.84	47	3.1 s
108	—	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
109	—	HyperNova 60B 2605OpenMultiverse Computing	22.1	$0.065	359	0.7 s
110	—	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	22.0	$0.15	126	2.4 s
111	—	ERNIE 5.0 Thinking PreviewClosedBaidu	21.9	—	—	—
112	▼ 31	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	21.8	$3.4	130	13 s
113	▼ 1	Grok Code Fast 1ClosedxAI	21.6	—	—	—
114	▼ 1	Nemotron Cascade 2 30B A3BOpenNVIDIA	21.3	—	—	—
115	▼ 1	Qwen3 Coder NextOpenAlibaba	21.2	$0.56	71	2.0 s
116	▼ 1	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.0	$0.83	—	—
117	▼ 1	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	20.9	$0.85	—	—
118	▼ 1	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	20.8	$0.26	169	0.8 s
119	▼ 1	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.2	56	3.1 s
120	▼ 1	North Mini CodeOpenCohere	20.6	$0.000	152	0.3 s
121	▼ 36	Nova 2.0 Lite (high)ClosedAmazon · 3 more variants	20.5	$0.85	135	32 s
122	▼ 2	Magistral Medium 1.2ClosedMistral	20.1	$2.8	41	1.8 s
123	▼ 2	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.1	$0.060	28	0.9 s
124	▼ 2	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.1	$2.1	—	—
125	▼ 2	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	20.1	$0.85	226	15 s
126	▼ 2	GPT-5 nano (high)ClosedOpenAI · 2 more variants	19.9	$0.14	164	89 s
127	▼ 2	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	19.8	$1.9	173	2.2 s
128	▼ 2	GLM-4.5 (Reasoning)OpenZ AI	19.5	$1.0	51	3.4 s
129	▼ 2	GPT-4.1ClosedOpenAI	19.4	$3.5	98	1.0 s
130	▼ 2	Ling 2.6 FlashOpenInclusionAI	19.3	$0.15	—	—
131	▼ 1	Qwen3.5 Omni FlashClosedAlibaba	19.0	$0.28	246	2.0 s
132	▼ 1	o3-miniClosedOpenAI · 1 more variant	19.0	$1.9	185	7.8 s
133	▼ 1	o1-proClosedOpenAI	18.9	$263	—	—
134	▼ 1	JT-MINIClosedChina Mobile	18.5	—	—	—
135	▼ 1	Grok 3ClosedxAI	18.4	$8.0	—	—
136	▼ 1	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	35	3.1 s
137	▼ 1	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$0.36	57	2.3 s
138	▼ 1	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$0.68	59	3.0 s
139	▼ 1	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	90	2.8 s
140	▼ 1	Sonar Reasoning ProClosedPerplexity	17.8	—	—	—
141	—	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
142	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	17.5	$0.096	75	3.7 s
143	—	LongCat Flash LiteOpenLongCat	17.2	$0.000	—	—
144	—	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.8	$0.45	86	3.9 s
145	—	GLM-4.5-AirOpenZ AI	16.5	$0.37	79	2.8 s
146	—	Mi:dm K 2.5 ProClosedKorea Telecom	16.4	—	—	—
147	—	GPT-4.1 miniClosedOpenAI	16.3	$0.70	78	0.8 s
148	—	Mistral Large 3OpenMistral	16.2	$0.75	50	1.2 s
149	—	Ring-1TOpenInclusionAI	16.2	—	—	—
150	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	15.8	$0.67	143	2.5 s
151	—	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.7	$1.2	—	—
152	—	INTELLECT-3OpenPrime Intellect	15.6	—	—	—
153	—	Devstral 2OpenMistral	15.5	$0.000	44	1.4 s
154	—	Solar Open 100B (Reasoning)OpenUpstage	15.1	—	—	—
155	—	Grok 3 Reasoning BetaClosedxAI	15.1	—	—	—
156	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	15.1	$0.18	—	—
157	—	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	278	1.0 s
158	▼ 18	gpt-oss-20B (high)OpenOpenAI · 1 more variant	14.9	$0.088	215	0.8 s
159	▼ 1	Mistral Medium 3.1ClosedMistral	14.8	$0.80	83	1.6 s
160	▼ 1	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
161	▼ 1	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$0.70	51	2.7 s
162	▲ 20	Llama 4 MaverickOpenMeta	14.3	$0.48	93	1.0 s
163	▼ 34	Solar Pro 3ClosedUpstage	14.1	—	—	—
164	▼ 3	o1-miniClosedOpenAI	14.0	—	—	—
165	▼ 3	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	176	2.2 s
166	▼ 3	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.35	100	2.7 s
167	▼ 3	GPT-4.5 (Preview)ClosedOpenAI	13.6	—	—	—
168	▼ 3	QwQ 32BOpenAlibaba	13.4	$0.75	30	2.1 s
169	▼ 3	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.34	111	2.3 s
170	▼ 3	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	13.3	—	—	—
171	▼ 3	Devstral Small 2OpenMistral	13.1	$0.000	45	1.2 s
172	▼ 3	Motif-2-12.7B-ReasoningClosedMotif Technologies	12.8	—	—	—
173	▼ 3	Ling-1TOpenInclusionAI	12.8	—	—	—
174	▼ 3	Nova PremierClosedAmazon	12.7	$5.0	33	2.9 s
175	▼ 3	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage · 3 more variants	12.5	—	—	—
176	▼ 3	Magistral Medium 1ClosedMistral	12.5	—	—	—
177	▼ 3	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	12.5	—	—	—
178	▼ 3	Mistral Medium 3ClosedMistral	12.5	$0.80	47	1.5 s
179	▼ 3	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	12.4	$0.18	48	1.3 s
180	▼ 3	Claude 3.5 HaikuClosedAnthropic	12.4	$1.6	—	—
181	▼ 3	Devstral MediumClosedMistral	12.4	$0.80	46	1.2 s
182	▼ 3	GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants	12.3	—	—	—
183	▼ 3	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	12.3	$0.26	—	—
184	▼ 3	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	12.2	—	—	—
185	▼ 2	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.0	—	—	—
186	▼ 2	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	12.0	—	—	—
187	▼ 2	Magistral Small 1.2OpenMistral	11.9	$0.75	105	0.9 s
188	▼ 2	Sarvam 105B (high)OpenSarvam	11.9	$0.074	103	2.1 s
189	▼ 2	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	11.8	—	—	—
190	▼ 2	Devstral Small (May '25)OpenMistral · 1 more variant	11.8	—	—	—
191	▼ 2	Claude 3 OpusClosedAnthropic	11.8	$30	—	—
192	▼ 2	Sonar ReasoningClosedPerplexity	11.7	—	—	—
193	▼ 2	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	11.4	$0.18	285	17 s
194	▼ 1	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	67	2.7 s
195	▼ 1	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
196	▼ 1	Magistral Small 1OpenMistral	10.7	—	—	—
197	▼ 1	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	10.6	—	—	—
198	▼ 1	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	110	2.5 s
199	▼ 1	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.28	61	2.7 s
200	▼ 1	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
201	▼ 1	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	10.2	$0.040	27	0.8 s
202	▼ 1	Qwen2.5 MaxClosedAlibaba	10.2	$2.8	—	—
203	▼ 1	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.1	$0.73	63	2.7 s
204	▼ 1	Nanbeige4.1-3BOpenNanbeige	10.1	—	—	—
205	▲ 38	Llama 4 ScoutOpenMeta	10.0	$0.29	109	0.9 s
206	▼ 2	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.30	112	2.3 s
207	▼ 2	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	10.0	—	—	—
208	▼ 2	Ministral 3 14BOpenMistral	10.0	$0.20	90	0.8 s
209	▼ 2	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	52	0.6 s
210	▼ 2	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	9.9	$6.0	—	—
211	▼ 2	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
212	▼ 2	Falcon-H1R-7BOpenTII UAE	9.8	—	—	—
213	▼ 2	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	59	2.3 s
214	▼ 2	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	86	2.1 s
215	▼ 2	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.37	—	—
216	▼ 2	SonarClosedPerplexity	9.5	—	—	—
217	▼ 2	Step3 VL 10BOpenStepFun	9.5	—	—	—
218	▼ 2	Sonar ProClosedPerplexity	9.3	—	—	—
219	▼ 2	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	9.3	—	—	—
220	▼ 2	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
221	▼ 2	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.1	$0.90	24	2.3 s
222	▼ 2	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	9.1	$3.0	53	1.2 s
223	▼ 2	Mistral Small 3.2OpenMistral	9.1	$0.13	138	0.7 s
224	▼ 2	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	51	2.4 s
225	▼ 2	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.21	145	2.0 s
226	▼ 2	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
227	▼ 2	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	9.0	$0.30	283	0.4 s
228	▼ 2	Ministral 3 8BOpenMistral	8.9	$0.15	96	0.7 s
229	—	Granite 4.1 30BOpenIBM	8.9	—	—	—
230	▼ 3	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	8.8	$0.070	78	7.4 s
231	▼ 3	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	8.8	—	—	—
232	▼ 2	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.8	—	—	—
233	▼ 2	Llama 3.3 Instruct 70BOpenMeta	8.6	$0.61	92	1.6 s
234	▼ 2	Mistral Small 3.1OpenMistral	8.6	$0.14	153	0.8 s
235	▼ 2	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
236	▼ 2	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
237	▼ 45	Llama 3.1 Instruct 405BOpenMeta	8.5	$3.7	32	2.3 s
238	▼ 3	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	121	2.3 s
239	▼ 3	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	234	2.6 s
240	▼ 3	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
241	▼ 3	Pixtral LargeOpenMistral	8.1	$3.0	49	1.2 s
242	▼ 3	Grok 2 (Dec '24)OpenxAI	8.0	—	—	—
243	▼ 3	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	8.0	—	—	—
244	▼ 3	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
245	▼ 3	GPT-4 TurboClosedOpenAI	7.9	$15	28	3.3 s
246	▼ 2	Nova ProClosedAmazon	7.7	$1.4	—	—
247	▼ 2	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	274	4.8 s
248	▼ 2	Grok BetaClosedxAI	7.5	—	—	—
249	▼ 2	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
250	▼ 2	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	7.4	$0.37	38	3.7 s
251	▼ 2	GPT-4.1 nanoClosedOpenAI	7.3	$0.18	148	0.6 s
252	▼ 2	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
253	▼ 2	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
254	▼ 2	GPT-4ClosedOpenAI	7.0	$38	—	—
255	▼ 2	Mistral Small 3OpenMistral	6.9	$0.10	150	0.8 s
256	▼ 1	Nova LiteClosedAmazon	6.9	$0.11	163	1.0 s
257	▼ 1	GPT-4o miniClosedOpenAI	6.9	$0.26	64	1.6 s
258	▼ 1	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.8	—	—	—
259	▼ 1	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	31	1.8 s
260	▼ 1	Granite 4.1 8BOpenIBM	6.7	$0.063	123	0.8 s
261	▼ 1	Sarvam 30B (high)OpenSarvam	6.6	$0.047	161	1.9 s
262	—	Mistral SabaClosedMistral	6.4	—	—	—
263	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
264	—	R1 1776OpenPerplexity	6.3	—	—	—
265	—	Qwen2.5 TurboClosedAlibaba	6.3	$0.088	104	2.4 s
266	—	Reka Flash (Sep '24)ClosedReka AI	6.3	$0.35	58	2.5 s
267	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	$1.4	57	1.2 s
267	—	Solar MiniOpenUpstage	6.2	$0.15	—	—
269	—	Llama 3.1 Instruct 8BOpenMeta	6.1	$0.10	154	0.9 s
270	—	Grok-1OpenxAI	6.0	—	—	—
271	—	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
272	—	Ministral 3 3BOpenMistral	5.6	$0.10	166	0.6 s
273	—	Gemini 1.5 Flash-8BClosedGoogle	5.5	—	—	—
274	—	Jamba 1.7 LargeOpenAI21 Labs	5.3	$3.5	59	1.6 s
275	—	Granite 4.0 H SmallOpenIBM	5.2	$0.11	356	10 s
276	—	Jamba 1.5 LargeOpenAI21 Labs	5.1	$3.5	—	—
277	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	95	2.0 s
278	—	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
279	—	Jamba 1.6 LargeOpenAI21 Labs	5.0	$3.5	60	1.6 s
280	—	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.0	$0.020	32	0.8 s
281	—	LFM2 24B A2BOpenLiquid AI	4.9	$0.053	126	0.6 s
282	—	Phi-4OpenMicrosoft	4.9	$0.22	40	2.0 s
283	—	Gemma 3 27B InstructOpenGoogle	4.8	$0.14	—	—
284	—	Claude 3 SonnetClosedAnthropic	4.7	$6.0	—	—
285	—	Nova MicroClosedAmazon	4.7	$0.061	294	1.0 s
286	—	Mistral Small (Sep '24)OpenMistral · 1 more variant	4.7	$0.30	155	0.8 s
287	—	Gemini 1.0 UltraClosedGoogle	4.6	—	—	—
288	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
289	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
290	—	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	16	1.8 s
291	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
292	—	Mistral Large (Feb '24)ClosedMistral	4.4	$6.0	—	—
293	—	Mixtral 8x22B InstructOpenMistral	4.4	—	—	—
294	—	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
295	—	Llama 3.2 Instruct 3BOpenMeta	4.2	$0.15	51	1.1 s
296	▼ 42	MiniCPM-V 4.6 1.3BOpenOpenBMB	4.2	—	—	—
297	▼ 1	Jamba Reasoning 3BOpenAI21 Labs	4.1	—	—	—
298	▼ 1	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
299	▼ 1	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
300	▼ 1	Reka Flash 3OpenReka AI	4.1	$0.35	—	—
301	▼ 1	Claude 2.1ClosedAnthropic	3.9	—	—	—
302	▼ 41	Claude 3 HaikuClosedAnthropic	3.9	$0.50	—	—
303	▼ 2	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
304	▼ 2	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
305	▼ 2	Claude 2.0ClosedAnthropic	3.6	—	—	—
305	▼ 2	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
307	▼ 2	Mistral MediumClosedMistral	3.6	$4.1	123	2.3 s
308	▼ 2	GPT-3.5 TurboClosedOpenAI	3.6	$0.75	—	—
309	▼ 2	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
310	▼ 2	Arctic InstructOpenSnowflake	3.4	—	—	—
310	▼ 2	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
312	▼ 2	Gemma 3 12B InstructOpenGoogle	3.4	$0.14	—	—
313	▼ 2	LFM 40BClosedLiquid AI	3.4	—	—	—
314	▼ 2	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.25	51	0.7 s
315	▼ 2	PALM-2ClosedGoogle	3.2	—	—	—
316	▼ 2	Granite 4.1 3BOpenIBM	3.2	—	—	—
317	▼ 2	Gemini 1.0 ProClosedGoogle	3.1	—	—	—
318	▼ 2	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
319	▼ 2	Sarvam M (Reasoning)OpenSarvam	3.0	$0.000	—	—
320	▼ 2	Phi-4 Mini InstructOpenMicrosoft	3.0	$0.000	45	0.9 s
321	▼ 2	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
321	▼ 2	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
323	▼ 2	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
324	▼ 2	Command-R+ (Apr '24)OpenCohere · 1 more variant	3.0	$6.0	—	—
325	▼ 2	OpenChat 3.5 (1210)OpenOpenChat	3.0	—	—	—
326	▼ 2	DBRX InstructOpenDatabricks	3.0	—	—	—
327	▼ 2	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	2.9	—	—	—
328	▼ 2	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
329	▼ 2	Jamba 1.7 MiniOpenAI21 Labs	2.7	—	—	—
330	▼ 2	LFM2 2.6BOpenLiquid AI	2.7	$0.000	338	1.3 s
331	▼ 2	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	$0.000	448	1.3 s
332	▼ 2	Jamba 1.5 MiniOpenAI21 Labs	2.7	$0.25	—	—
333	▼ 2	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
334	▼ 2	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.6	$0.40	—	—
335	▼ 2	Jamba 1.6 MiniOpenAI21 Labs	2.6	$0.25	182	1.0 s
336	▼ 2	Mixtral 8x7B InstructOpenMistral	2.4	$0.51	—	—
337	▼ 2	Gemma 3 270MOpenGoogle	2.4	—	—	—
338	▼ 2	Apertus 70B InstructOpenSwiss AI Initiative	2.4	$1.3	—	—
339	▼ 2	Granite 4.0 MicroOpenIBM	2.4	—	—	—
340	▼ 2	Claude InstantClosedAnthropic	2.1	—	—	—
340	▼ 2	Llama 65BOpenMeta	2.1	—	—	—
340	▼ 2	Mistral 7B InstructOpenMistral	2.1	$0.21	96	0.7 s
340	▼ 2	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
344	▼ 2	Granite 4.0 1BOpenIBM	2.1	—	—	—
345	▼ 2	LFM2 8B A1BOpenLiquid AI	1.8	$0.000	—	—
346	▼ 2	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	348	28 s
347	▼ 2	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	1.3	$0.40	—	—
348	▼ 2	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
349	▼ 2	Gemma 3n E4B InstructOpenGoogle	1.2	$0.025	52	1.3 s
350	▼ 2	LFM2 1.2BOpenLiquid AI	1.1	$0.000	430	1.3 s
351	▼ 2	Gemma 3 4B InstructOpenGoogle	1.1	$0.050	—	—
352	▼ 2	Llama 3.2 Instruct 1BOpenMeta	1.1	$0.050	84	0.9 s
353	▼ 2	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	467	1.6 s
354	▼ 1	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
354	—	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
354	▲ 2	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
354	▼ 2	Granite 4.0 350MOpenIBM	1.0	—	—	—
354	▲ 1	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
354	▲ 3	Tiny Aya GlobalOpenCohere	1.0	$0.000	—	—

309 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