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	60	103 s
2	—	GPT-5.6 Sol (max)ClosedOpenAI	58.9	$11	72	170 s
3	—	GPT-5.6 Sol (xhigh)ClosedOpenAI	57.7	$11	69	59 s
4	—	GPT-5.6 Sol (high)ClosedOpenAI	55.9	$11	68	13 s
5	—	Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic	55.7	$10	56	46 s
6	—	GPT-5.6 Terra (max)ClosedOpenAI	55.0	$5.6	141	155 s
7	—	GPT-5.5 (xhigh)ClosedOpenAI	54.8	$11	69	98 s
8	—	Grok 4.5 (high)ClosedSpaceXAI	53.8	$3.0	116	13 s
9	—	GPT-5.6 Sol (medium)ClosedOpenAI	53.6	$11	61	5.4 s
10	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic	53.5	$10	47	23 s
11	—	Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic	53.4	$4.0	77	221 s
12	—	GPT-5.5 (high)ClosedOpenAI	53.1	$11	70	31 s
13	—	GPT-5.6 Terra (xhigh)ClosedOpenAI	51.6	$5.6	125	41 s
14	—	GPT-5.4 (xhigh)ClosedOpenAI	51.4	$5.6	156	113 s
15	—	GPT-5.6 Luna (max)ClosedOpenAI	51.2	$2.3	217	99 s
16	—	GLM-5.2 (max)OpenZ AI	51.1	$2.2	191	1.4 s
17	—	Muse Spark 1.1 (xhigh)ClosedMeta	50.6	$2.0	119	1.1 s
18	—	GPT-5.5 (medium)ClosedOpenAI	50.4	$11	62	10 s
19	—	Gemini 3.5 Flash (high)ClosedGoogle	50.2	$3.4	152	24 s
20	—	GPT-5.6 Sol (low)ClosedOpenAI	49.4	$11	64	2.3 s
21	—	GPT-5.6 Luna (xhigh)ClosedOpenAI	49.1	$2.3	196	39 s
22	—	GPT-5.6 Terra (high)ClosedOpenAI	49.0	$5.6	120	4.8 s
23	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic	47.2	$6.0	66	164 s
24	—	Gemini 3.1 Pro PreviewClosedGoogle	46.5	$4.5	128	25 s
25	—	GPT-5.6 Luna (high)ClosedOpenAI	46.1	$2.3	191	13 s
26	—	Qwen3.7 MaxClosedAlibaba	46.0	$3.8	198	2.5 s
27	—	GPT-5.6 Terra (medium)ClosedOpenAI	45.6	$5.6	116	1.4 s
28	—	Gemini 3.5 Flash (medium)ClosedGoogle	45.4	$3.4	149	20 s
29	—	MiniMax-M3OpenMiniMax	44.4	$0.52	108	1.4 s
30	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek	44.3	$0.54	62	1.8 s
31	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	44.3	$4.8	91	75 s
32	—	Kimi K2.6OpenKimi	44.2	$1.7	47	2.2 s
33	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic	43.7	$10	43	26 s
34	—	GPT-5.5 (low)ClosedOpenAI	43.5	$11	58	2.0 s
35	—	Muse SparkClosedMeta	43.1	—	—	—
36	—	Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic	42.7	$10	43	1.6 s
37	—	MiMo-V2.5-ProOpenXiaomi	42.2	$0.54	51	3.8 s
38	—	GPT-5.2 (xhigh)ClosedOpenAI	42.2	$4.8	74	150 s
39	—	Kimi K2.7 CodeOpenKimi	41.9	$1.7	49	3.1 s
40	—	Claude Sonnet 5 (Non-reasoning, High Effort)ClosedAnthropic	41.7	$4.0	68	1.4 s
41	—	GPT-5.6 Sol (Non-reasoning)ClosedOpenAI	41.2	$11	—	—
42	—	Nex-N2-ProOpenNex AGI	41.0	$1.0	133	1.7 s
43	—	DeepSeek V4 Pro (Reasoning, High Effort)OpenDeepSeek	40.8	$0.54	58	1.7 s
44	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic	40.8	$10	48	17 s
45	—	GPT-5.6 Terra (low)ClosedOpenAI	40.5	$5.6	112	1.4 s
46	—	MiMo-V2-ProClosedXiaomi	40.3	$1.5	—	—
47	—	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek	40.3	$0.18	102	1.4 s
48	—	GLM-5.1 (Reasoning)OpenZ AI	40.2	$2.2	71	1.4 s
49	—	GPT-5.2 Codex (xhigh)ClosedOpenAI	40.1	$4.8	160	74 s
50	—	Qwen3.6 Max PreviewClosedAlibaba	40.0	$2.9	54	3.3 s
51	—	GPT-5.4 mini (xhigh)ClosedOpenAI	40.0	$1.7	164	9.2 s
52	—	Grok Build 0.1 0616ClosedSpaceXAI	39.8	$1.3	60	0.5 s
53	—	Qwen3.6 PlusClosedAlibaba	39.6	$1.1	52	2.7 s
54	—	Gemini 3 Pro Preview (high)ClosedGoogle	39.6	$4.5	—	—
55	—	GLM-5 (Reasoning)OpenZ AI	39.5	$1.6	52	1.8 s
56	—	GPT-5.4 (low)ClosedOpenAI	39.1	$5.6	100	1.5 s
57	—	Qwen3.7 PlusClosedAlibaba	39.0	$0.70	52	3.0 s
58	—	JT-4.1 Flash 236B A21BClosedChina Mobile	38.8	—	—	—
59	—	GPT-5.4 nano (xhigh)ClosedOpenAI	38.2	$0.46	171	7.4 s
60	—	MiniMax-M2.7OpenMiniMax	38.1	$0.52	47	1.9 s
61	—	Kimi K2.5 (Reasoning)OpenKimi	38.1	$1.2	55	2.9 s
62	—	GLM-5-TurboClosedZ AI	38.1	—	—	—
63	—	GPT-5.6 Luna (medium)ClosedOpenAI	38.1	$2.3	196	2.0 s
64	—	GPT-5.2 (medium)ClosedOpenAI	38.0	$4.8	—	—
65	—	Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic	37.8	$10	37	2.3 s
66	—	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	37.8	$1.2	194	1.1 s
67	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle	37.8	$1.1	172	6.9 s
68	—	Grok 4.3 (high)ClosedSpaceXAI	37.6	$1.6	117	24 s
69	—	DeepSeek V4 Flash (Reasoning, High Effort)OpenDeepSeek	37.4	$0.18	—	—
70	—	MiMo-V2.5OpenXiaomi	37.2	$0.18	80	2.6 s
71	—	Qwen3.6 27B (Reasoning)OpenAlibaba	37.1	$1.4	58	3.8 s
72	—	Grok 4.20 0309 v2 (Reasoning)ClosedSpaceXAI	37.0	$3.0	145	15 s
73	—	GPT-5.1 (high)ClosedOpenAI	36.9	$3.4	101	40 s
74	—	Grok 4.20 0309 (Reasoning)ClosedSpaceXAI	36.5	$3.0	—	—
75	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic	36.4	$6.0	41	14 s
76	—	MiMo-V2-Omni-0327ClosedXiaomi	36.4	$0.80	—	—
77	—	GPT-5 Codex (high)ClosedOpenAI	36.1	$3.4	172	8.5 s
78	—	Grok 4.3 (medium)ClosedSpaceXAI	36.0	$1.6	104	13 s
79	—	Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic	35.9	$6.0	43	1.3 s
80	—	Grok 4.3 (low)ClosedSpaceXAI	35.4	$1.6	116	5.2 s
81	—	KAT Coder Pro V2ClosedKwaiKAT	35.4	$0.52	—	—
82	—	GPT-5.5 (Non-reasoning)ClosedOpenAI	35.4	$11	60	0.9 s
83	—	GLM-5.1 (Non-reasoning)OpenZ AI	35.4	$2.2	62	1.8 s
84	—	MiMo-V2-OmniClosedXiaomi	35.0	$0.000	—	—
85	—	Gemini 3.5 Flash (minimal)ClosedGoogle	34.9	$3.4	152	0.9 s
86	—	GPT-5.1 Codex (high)ClosedOpenAI	34.7	$3.4	167	7.7 s
87	—	GPT-5 (high)ClosedOpenAI	34.7	$3.4	87	81 s
88	—	Claude Opus 4.5 (Non-reasoning)ClosedAnthropic	34.7	$10	46	1.6 s
89	—	KAT-Coder-Pro V1ClosedKwaiKAT	34.6	$0.52	104	1.3 s
90	—	Kimi K2.6 (Non-reasoning)OpenKimi	34.6	$1.7	44	2.3 s
91	—	GLM 5V Turbo (Reasoning)ClosedZ AI	34.5	—	—	—
92	—	Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic	34.3	$6.0	43	1.5 s
93	—	GLM-5.2 (Non-reasoning)OpenZ AI	34.1	$3.2	109	1.6 s
94	—	GPT-5.6 Terra (Non-reasoning)ClosedOpenAI	34.0	$5.6	116	0.7 s
95	—	Qwen3.5 27B (Reasoning)OpenAlibaba	33.8	$0.83	80	5.7 s
96	—	GPT-5 (medium)ClosedOpenAI	33.7	$3.4	89	37 s
97	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic	33.7	$30	29	15 s
98	—	GLM-4.7 (Reasoning)OpenZ AI	33.7	$1.0	142	0.8 s
99	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	33.7	$1.4	59	2.6 s
100	—	MiniMax-M2.5OpenMiniMax	33.7	$0.52	79	1.8 s
101	—	Hy3-preview (Reasoning)OpenTencent	33.6	$0.20	169	3.1 s
102	—	GPT-5.5 Instant (May 2026)ClosedOpenAI	33.5	$11	—	—
103	—	Grok 4ClosedSpaceXAI	33.3	$11	—	—
104	—	GPT-5.6 Luna (low)ClosedOpenAI	33.3	$2.3	195	1.3 s
105	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi	33.2	$0.15	—	—
106	—	Gemini 3 Pro Preview (low)ClosedGoogle	33.1	$4.5	—	—
107	—	Kimi K2 ThinkingOpenKimi	32.7	$1.1	162	1.2 s
108	—	o3-proClosedOpenAI	32.5	$35	36	68 s
109	—	GLM-5 (Non-reasoning)OpenZ AI	32.4	$1.6	63	1.4 s
110	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	32.3	$1.1	143	2.4 s
111	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek	32.0	$0.32	—	—
112	—	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	32.0	$1.4	60	2.6 s
113	—	Qwen3 Max ThinkingClosedAlibaba	31.7	—	—	—
114	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	31.6	$0.56	171	2.4 s
115	—	MiniMax-M2.1OpenMiniMax	31.4	$0.52	84	1.8 s
116	—	DeepSeek V4 Pro (Non-reasoning)OpenDeepSeek	31.2	$0.54	61	1.8 s
117	—	MiMo-V2-Flash (Reasoning)OpenXiaomi	31.2	$0.15	—	—
118	—	GPT-5 (low)ClosedOpenAI	31.2	$3.4	68	12 s
119	—	Claude 4 Opus (Reasoning)ClosedAnthropic	31.0	$30	—	—
120	—	GPT-5 mini (medium)ClosedOpenAI	30.9	$0.69	105	17 s
121	—	Qwen3.5 Omni PlusClosedAlibaba	30.6	$1.5	56	2.5 s
122	—	GPT-5.1 Codex mini (high)ClosedOpenAI	30.6	$0.69	207	14 s
123	—	Grok 4.1 Fast (Reasoning)ClosedSpaceXAI	30.6	—	—	—
124	—	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	125	3.3 s
125	—	Qwen3.6 27B (Non-reasoning)OpenAlibaba	30.5	$1.4	55	3.6 s
126	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	30.4	$1.9	—	—
127	—	o3ClosedOpenAI	30.4	$3.5	123	6.0 s
128	—	Step 3.7 FlashOpenStepFun	30.3	$0.44	381	0.9 s
129	—	GPT-5.4 nano (medium)ClosedOpenAI	30.2	$0.46	165	5.4 s
130	—	Mistral Medium 3.5OpenMistral	29.9	$3.0	135	2.1 s
131	—	GPT-5.4 mini (medium)ClosedOpenAI	29.8	$1.7	152	10 s
132	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic	29.6	$2.0	102	19 s
133	—	Kimi K2.5 (Non-reasoning)OpenKimi	29.4	$1.2	53	2.8 s
134	—	Gemma 4 31B (Reasoning)OpenGoogle	29.4	$0.000	35	1.1 s
135	—	Qwen3.5 27B (Non-reasoning)OpenAlibaba	29.3	$0.83	87	5.7 s
136	—	Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic	29.3	$6.0	39	1.7 s
137	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba	29.3	$0.69	160	2.3 s
138	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic	28.9	$6.0	—	—
139	—	GPT-5.5 Instant (June 2026)ClosedOpenAI	28.9	$11	—	—
140	—	GLM-4.6 (Reasoning)OpenZ AI	28.7	$0.96	46	1.4 s
141	—	DeepSeek V4 Flash (Non-reasoning)OpenDeepSeek	28.7	$0.18	100	1.2 s
142	—	JT-35B-FlashClosedChina Mobile	28.4	—	—	—
143	—	MiniMax-M2OpenMiniMax	28.3	$0.52	81	1.9 s
144	—	Claude 4.1 Opus (Non-reasoning)ClosedAnthropic	28.2	$30	29	2.3 s
145	—	MiMo-V2.5-Pro (Non-reasoning)OpenXiaomi	27.9	$0.93	66	2.2 s
146	—	GPT-5.4 (Non-reasoning)ClosedOpenAI	27.7	$5.6	98	0.7 s
147	—	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	27.6	$1.1	162	2.5 s
148	—	Grok 4 Fast (Reasoning)ClosedSpaceXAI	27.4	$0.28	—	—
149	—	Gemini 3 Flash Preview (Non-reasoning)ClosedGoogle	27.4	$1.1	163	0.8 s
150	—	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic	27.1	—	—	—
151	—	GPT-5.6 Luna (Non-reasoning)ClosedOpenAI	26.6	$2.3	192	0.7 s
152	—	GLM-4.7 (Non-reasoning)OpenZ AI	26.6	$1.0	135	0.8 s
153	—	Hy3-preview (Non-reasoning)OpenTencent	26.1	$0.20	165	3.1 s
154	—	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
155	—	GPT-5.2 (Non-reasoning)ClosedOpenAI	26.0	$4.8	65	1.0 s
156	—	Step 3.5 Flash 2603ClosedStepFun	26.0	$0.15	200	1.0 s
157	—	Doubao Seed CodeClosedByteDance Seed	26.0	—	—	—
158	—	Gemini 2.5 ProClosedGoogle	25.8	$3.4	139	19 s
159	—	Gemma 4 26B A4B (Reasoning)OpenGoogle	25.7	$0.20	—	—
160	—	o4-mini (high)ClosedOpenAI	25.6	$1.9	165	23 s
161	—	Step 3.5 FlashOpenStepFun	25.5	$0.15	195	1.1 s
162	—	Claude 4 Opus (Non-reasoning)ClosedAnthropic	25.5	$30	—	—
163	—	Claude 4 Sonnet (Non-reasoning)ClosedAnthropic	25.5	$6.0	—	—
164	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	25.4	$0.32	—	—
165	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	25.4	$0.38	146	1.1 s
166	—	Mercury 2ClosedInception	25.3	$0.38	783	3.0 s
167	—	GPT-5 mini (high)ClosedOpenAI	25.3	$0.69	102	74 s
168	—	Gemini 3.1 Flash-LiteClosedGoogle	25.0	$0.56	272	5.8 s
169	—	Qwen3 Max Thinking (Preview)ClosedAlibaba	25.0	$2.4	59	4.0 s
170	—	Grok 4.3 (Non-reasoning)ClosedSpaceXAI	24.8	$1.6	116	0.8 s
171	—	K-EXAONE (Reasoning)OpenLG AI Research	24.7	—	—	—
172	—	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	24.7	$0.15	—	—
173	—	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	24.7	$0.32	—	—
174	—	Trinity Large ThinkingOpenArcee AI	24.5	$0.40	218	1.2 s
175	—	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	24.2	$0.84	183	2.4 s
176	—	Qwen3 MaxClosedAlibaba	24.0	$2.4	53	2.5 s
177	—	gpt-oss-120b (high)OpenOpenAI	23.8	$0.26	319	0.8 s
178	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle	23.8	—	—	—
179	—	Claude 4.5 Haiku (Non-reasoning)ClosedAnthropic	23.7	$2.0	91	1.0 s
180	—	Kimi K2 0905OpenKimi	23.5	$1.1	37	2.0 s
181	—	Claude 3.7 Sonnet (Non-reasoning)ClosedAnthropic	23.5	$6.0	—	—
182	—	o1ClosedOpenAI	23.4	$26	101	30 s
183	—	Qwen3.5 35B A3B (Non-reasoning)OpenAlibaba	23.4	$0.69	196	2.2 s
184	—	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle	23.0	—	—	—
185	—	GLM-4.6 (Non-reasoning)OpenZ AI	23.0	$0.98	40	3.7 s
186	—	EXAONE 4.5 33BOpenLG AI Research	23.0	—	—	—
187	—	GLM-4.7-Flash (Reasoning)OpenZ AI	22.9	$0.15	90	1.2 s
188	—	Command A+OpenCohere	22.5	$0.000	164	0.4 s
189	—	Grok 3 mini Reasoning (high)ClosedSpaceXAI	22.5	$0.35	50	0.8 s
190	—	Grok 4.20 0309 (Non-reasoning)ClosedSpaceXAI	22.5	$3.0	—	—
191	—	Gemini 2.5 Pro Preview (May' 25)ClosedGoogle	22.3	$3.4	—	—
192	—	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
193	—	Gemma 4 12B (Reasoning)OpenGoogle	22.0	$0.15	71	2.5 s
194	—	ERNIE 5.0 Thinking PreviewClosedBaidu	21.9	—	—	—
195	—	Grok 4.20 0309 v2 (Non-reasoning)ClosedSpaceXAI	21.8	$3.0	149	0.6 s
196	—	Gemma 4 31B (Non-reasoning)OpenGoogle	21.8	$0.21	52	2.2 s
197	—	Nova 2.0 Pro Preview (medium)ClosedAmazon	21.8	$3.4	126	15 s
198	—	Grok Code Fast 1ClosedSpaceXAI	21.6	—	—	—
199	—	Qwen3.5 9B (Reasoning)OpenAlibaba	21.4	$0.11	54	1.6 s
200	—	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	21.4	$0.45	—	—
201	—	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	21.3	$0.32	—	—
202	—	Nemotron Cascade 2 30B A3BOpenNVIDIA	21.3	—	—	—
203	—	Apriel-v1.5-15B-ThinkerOpenServiceNow	21.2	$0.000	—	—
204	—	Qwen3 Coder NextOpenAlibaba	21.1	$0.56	106	1.7 s
205	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	21.0	$0.84	—	—
206	—	Nova 2.0 Omni (medium)ClosedAmazon	20.9	$0.85	—	—
207	—	DeepSeek V3.1 (Reasoning)OpenDeepSeek	20.7	$0.87	—	—
208	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.6	56	3.0 s
209	—	North Mini CodeOpenCohere	20.6	$0.000	105	0.3 s
210	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	20.5	$0.000	—	—
211	—	GPT-5.1 (Non-reasoning)ClosedOpenAI	20.4	$3.4	101	1.1 s
212	—	Qwen3.5 9B (Non-reasoning)OpenAlibaba	20.3	—	—	—
213	—	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	20.1	$0.20	96	1.1 s
214	—	Qwen3.5 4B (Reasoning)OpenAlibaba	20.1	$0.060	24	0.7 s
215	—	DeepSeek R1 0528 (May '25)OpenDeepSeek	20.1	$2.1	—	—
216	—	Gemini 2.5 Flash (Reasoning)ClosedGoogle	20.1	$0.85	211	15 s
217	—	GPT-5 nano (high)ClosedOpenAI	19.9	$0.14	152	101 s
218	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	19.6	$2.6	58	2.9 s
219	—	Nova 2.0 Pro Preview (low)ClosedAmazon	19.6	$3.4	124	12 s
220	—	Mistral Small 4 (Reasoning)OpenMistral	19.6	$0.26	166	0.7 s
221	—	GLM-4.5 (Reasoning)OpenZ AI	19.5	$1.0	—	—
222	—	Kimi K2OpenKimi	19.4	$1.0	37	2.4 s
223	—	GPT-4.1ClosedOpenAI	19.4	$3.5	109	0.9 s
224	—	Qwen3 Max (Preview)ClosedAlibaba	19.2	$2.4	63	4.1 s
225	—	Devstral 2OpenMistral	19.2	$0.000	60	1.3 s
226	—	Nova 2.0 Lite (medium)ClosedAmazon	19.0	$0.85	149	17 s
227	—	GPT-5 nano (medium)ClosedOpenAI	19.0	$0.14	146	38 s
228	—	Qwen3.5 Omni FlashClosedAlibaba	19.0	$0.28	225	1.9 s
229	—	o3-miniClosedOpenAI	19.0	$1.9	226	6.2 s
230	—	o1-proClosedOpenAI	18.9	$263	—	—
231	—	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle	18.8	—	—	—
232	—	JT-MINIClosedChina Mobile	18.5	—	—	—
233	—	DeepSeek R1 (Jan '25)OpenDeepSeek	18.5	$2.4	—	—
234	—	Grok 3ClosedSpaceXAI	18.4	$8.0	—	—
235	—	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	36	3.0 s
236	—	Nova 2.0 Lite (high)ClosedAmazon	18.2	$0.85	161	19 s
237	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$1.2	57	2.1 s
238	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$3.0	58	3.1 s
239	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	90	2.7 s
240	—	Magistral Medium 1.2ClosedMistral	17.9	$2.8	41	1.7 s
241	—	Sonar Reasoning ProClosedPerplexity	17.8	—	—	—
242	—	Nova 2.0 Lite (low)ClosedAmazon	17.8	$0.85	143	13 s
243	—	HyperNova 60B 2605OpenMultiverse Computing	17.8	$0.065	354	1.0 s
244	—	gpt-oss-120b (low)OpenOpenAI	17.7	$0.26	335	0.8 s
245	—	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
246	—	GPT-5.4 nano (Non-Reasoning)ClosedOpenAI	17.6	$0.46	162	0.6 s
247	—	Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle	17.5	—	—	—
248	—	Devstral Small 2OpenMistral	17.4	$0.000	73	1.2 s
249	—	K2 Think V2OpenMBZUAI Institute of Foundation Models	17.3	—	—	—
250	—	LongCat Flash LiteOpenLongCat	17.2	—	—	—
251	—	GPT-5 (minimal)ClosedOpenAI	17.2	$3.4	60	1.3 s
252	—	o1-previewClosedOpenAI	17.0	$29	—	—
253	—	HyperCLOVA X SEED Think (32B)OpenNaver	17.0	—	—	—
254	—	Grok 4.1 Fast (Non-reasoning)ClosedSpaceXAI	16.9	—	—	—
255	—	GLM-4.6V (Reasoning)OpenZ AI	16.8	$0.45	59	4.3 s
256	—	K-EXAONE (Non-reasoning)OpenLG AI Research	16.7	—	—	—
257	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.7	$1.9	171	2.3 s
258	—	GPT-5.4 mini (Non-Reasoning)ClosedOpenAI	16.6	$1.7	149	0.8 s
259	—	Nova 2.0 Omni (low)ClosedAmazon	16.6	$0.85	—	—
260	—	GLM-4.5-AirOpenZ AI	16.5	$0.37	74	2.7 s
261	—	Grok 4 Fast (Non-reasoning)ClosedSpaceXAI	16.5	$0.28	—	—
262	—	Mi:dm K 2.5 ProClosedKorea Telecom	16.4	—	—	—
263	—	Ring-1TOpenInclusionAI	16.2	—	—	—
264	—	Qwen3.5 4B (Non-reasoning)OpenAlibaba	16.0	$0.060	30	0.7 s
265	—	Mistral Large 3OpenMistral	15.9	$0.75	47	1.2 s
266	—	o3-mini (high)ClosedOpenAI	15.6	$1.9	238	19 s
267	—	INTELLECT-3OpenPrime Intellect	15.6	—	—	—
268	—	GLM-4.7-Flash (Non-reasoning)OpenZ AI	15.5	$0.15	183	1.4 s
269	—	DeepSeek V3 0324OpenDeepSeek	15.4	$1.2	—	—
270	—	GPT-5 (ChatGPT)ClosedOpenAI	15.3	$3.4	165	0.8 s
271	—	Solar Open 100B (Reasoning)OpenUpstage	15.1	—	—	—
272	—	Grok 3 Reasoning BetaClosedSpaceXAI	15.1	—	—	—
273	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle	15.1	$0.18	—	—
274	—	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	14.9	$0.13	313	1.0 s
275	—	gpt-oss-20b (high)OpenOpenAI	14.9	$0.088	218	0.8 s
276	—	GPT-4.1 miniClosedOpenAI	14.8	$0.70	78	0.9 s
277	—	Mistral Small 3.1OpenMistral	14.7	$0.15	150	0.7 s
278	—	Mistral Medium 3.1ClosedMistral	14.7	$0.80	83	1.6 s
279	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	14.4	$0.75	119	2.5 s
280	—	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
281	—	Nova 2.0 Pro Preview (Non-reasoning)ClosedAmazon	14.4	$3.4	121	1.1 s
282	—	gpt-oss-20b (low)OpenOpenAI	14.3	$0.095	270	0.8 s
283	—	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$1.2	51	2.8 s
284	—	Llama 4 MaverickOpenMeta	14.3	$0.48	118	1.0 s
285	—	GPT-5 mini (minimal)ClosedOpenAI	14.3	$0.69	95	0.9 s
286	—	K2-V2 (high)OpenMBZUAI Institute of Foundation Models	14.2	—	—	—
287	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	14.2	$0.088	107	1.4 s
288	—	DeepSeek V3 (Dec '24)OpenDeepSeek	14.2	$0.52	—	—
289	—	Gemini 2.5 Flash (Non-reasoning)ClosedGoogle	14.1	$0.85	193	0.5 s
290	—	Solar Pro 3ClosedUpstage	14.1	—	—	—
291	—	Ling 2.6 FlashOpenInclusionAI	14.1	$0.15	172	1.2 s
292	—	o1-miniClosedOpenAI	14.0	—	—	—
293	—	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	181	2.3 s
294	—	Tri-21B-think PreviewOpenTrillion Labs	13.6	—	—	—
295	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	102	2.6 s
296	—	GPT-4.5 (Preview)ClosedOpenAI	13.6	—	—	—
297	—	DiffusionGemma 26B A4BOpenGoogle	13.5	—	—	—
298	—	Qwen3 235B A22B (Reasoning)OpenAlibaba	13.4	$2.6	62	2.9 s
299	—	QwQ 32BOpenAlibaba	13.4	$0.75	32	2.1 s
300	—	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.75	112	2.3 s
301	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle	13.3	—	—	—
302	—	Gemma 4 12B (Non-reasoning)OpenGoogle	13.2	$0.15	43	2.7 s
303	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)ClosedGoogle	13.1	$0.18	—	—
304	—	Motif-2-12.7B-ReasoningClosedMotif Technologies	12.8	—	—	—
305	—	Ling-1TOpenInclusionAI	12.8	—	—	—
306	—	Nova PremierClosedAmazon	12.7	$5.0	35	2.9 s
307	—	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage	12.5	—	—	—
308	—	Magistral Medium 1ClosedMistral	12.5	—	—	—
309	—	Gemma 4 E4B (Reasoning)OpenGoogle	12.5	—	—	—
310	—	Mistral Medium 3ClosedMistral	12.5	$0.80	47	1.5 s
311	—	K2-V2 (medium)OpenMBZUAI Institute of Foundation Models	12.4	—	—	—
312	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	12.4	$0.40	50	1.2 s
313	—	Devstral MediumClosedMistral	12.4	$0.80	—	—
314	—	Mistral Small 4 (Non-reasoning)OpenMistral	12.4	$0.26	149	0.7 s
315	—	Tri-21B-ThinkOpenTrillion Labs	12.4	—	—	—
316	—	GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI	12.3	—	—	—
317	—	Gemini 2.0 Flash (Feb '25)ClosedGoogle	12.3	$0.26	—	—
318	—	Claude 3.5 HaikuClosedAnthropic	12.3	$1.6	—	—
319	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	12.2	—	—	—
320	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba	12.0	—	—	—
321	—	MiniCPM5-1B (Reasoning)OpenOpenBMB	12.0	—	—	—
322	—	Sarvam 105B (high)OpenSarvam	11.9	$0.074	132	2.0 s
323	—	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	11.8	—	—	—
324	—	Nova 2.0 Lite (Non-reasoning)ClosedAmazon	11.8	$0.85	164	1.2 s
325	—	Devstral Small (May '25)OpenMistral	11.8	—	—	—
326	—	Claude 3 OpusClosedAnthropic	11.8	$30	—	—
327	—	MiniCPM5-1B (Non-reasoning)OpenOpenBMB	11.7	—	—	—
328	—	Sonar ReasoningClosedPerplexity	11.7	—	—	—
329	—	Gemini 2.5 Flash Preview (Non-reasoning)ClosedGoogle	11.7	—	—	—
330	—	Qwen3 32B (Reasoning)OpenAlibaba	11.5	$2.6	92	2.6 s
331	—	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle	11.4	$0.18	223	26 s
332	—	Magistral Small 1.2OpenMistral	11.3	$0.75	81	0.9 s
333	—	GPT-4o (Nov '24)ClosedOpenAI	11.2	$4.4	210	0.8 s
334	—	Nanbeige4.1-3BOpenNanbeige	11.1	—	—	—
335	—	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	72	2.7 s
336	—	Ministral 3 14BOpenMistral	11.1	$0.20	81	0.9 s
337	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
338	—	GLM-4.6V (Non-reasoning)OpenZ AI	11.0	$0.45	58	6.1 s
339	—	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	10.9	$1.2	62	2.9 s
340	—	Magistral Small 1OpenMistral	10.7	—	—	—
341	—	Gemini 2.0 Flash (experimental)ClosedGoogle	10.7	$0.000	—	—
342	—	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	10.6	—	—	—
343	—	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	111	2.4 s
344	—	Mistral Small 3.2OpenMistral	10.6	$0.15	153	0.6 s
345	—	Nova 2.0 Omni (Non-reasoning)ClosedAmazon	10.5	$0.85	—	—
346	—	Qwen3 14B (Reasoning)OpenAlibaba	10.4	$1.3	62	2.7 s
347	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
348	—	Qwen2.5 MaxClosedAlibaba	10.2	—	—	—
349	—	Llama 4 ScoutOpenMeta	10.0	$0.29	115	0.9 s
350	—	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.35	113	2.2 s
351	—	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research	10.0	$0.20	92	1.4 s
352	—	Gemini 1.5 Pro (Sep '24)ClosedGoogle	10.0	—	—	—
352	—	Solar Pro 2 (Preview) (Non-reasoning)ClosedUpstage	10.0	—	—	—
354	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	30	0.6 s
355	—	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic	9.9	$6.0	—	—
356	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
357	—	Falcon-H1R-7BOpenTII UAE	9.8	—	—	—
358	—	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	73	2.2 s
359	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	101	2.0 s
360	—	GPT-4o (Aug '24)ClosedOpenAI	9.6	$4.4	81	1.6 s
361	—	GPT-4.1 nanoClosedOpenAI	9.6	$0.18	154	0.7 s
362	—	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.48	—	—
363	—	SonarClosedPerplexity	9.5	—	—	—
364	—	Step3 VL 10BOpenStepFun	9.5	—	—	—
365	—	Llama 3.3 Instruct 70BOpenMeta	9.4	$0.61	90	1.6 s
366	—	Qwen3 30B A3B (Reasoning)OpenAlibaba	9.3	$0.75	103	2.3 s
367	—	Sonar ProClosedPerplexity	9.3	—	—	—
368	—	Devstral Small (Jul '25)OpenMistral	9.3	$0.15	—	—
369	—	Gemma 4 E2B (Reasoning)OpenGoogle	9.3	—	—	—
370	—	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
371	—	GLM-4.5V (Reasoning)OpenZ AI	9.1	$0.90	26	6.3 s
372	—	Mistral Large 2 (Nov '24)OpenMistral	9.1	$3.0	—	—
373	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	9.1	$0.90	51	2.4 s
374	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.35	141	2.0 s
375	—	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
376	—	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research	9.0	$1.5	41	2.4 s
377	—	Solar Pro 2 (Reasoning)ClosedUpstage	9.0	—	—	—
378	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	9.0	$0.30	285	0.4 s
379	—	Ministral 3 8BOpenMistral	9.0	$0.15	84	0.8 s
380	—	Gemma 4 E4B (Non-reasoning)OpenGoogle	8.9	—	—	—
381	—	Granite 4.1 30BOpenIBM	8.9	—	—	—
382	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	8.8	$0.070	86	6.4 s
383	—	Hermes 4 - Llama-3.1 405B (Non-reasoning)OpenNous Research	8.8	$1.5	41	2.4 s
384	—	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle	8.8	—	—	—
385	—	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	8.7	—	—	—
386	—	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	8.7	$0.40	51	1.2 s
387	—	Qwen3 32B (Non-reasoning)OpenAlibaba	8.6	$1.2	96	2.5 s
388	—	GPT-4o (May '24)ClosedOpenAI	8.6	$7.5	94	1.1 s
389	—	Gemini 2.0 Flash-Lite (Preview)ClosedGoogle	8.6	—	—	—
390	—	K2-V2 (low)OpenMBZUAI Institute of Foundation Models	8.6	—	—	—
391	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	8.5	—	—	—
392	—	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
393	—	Llama 3.1 Instruct 405BOpenMeta	8.5	$3.7	75	2.4 s
394	—	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	8.5	—	—	—
395	—	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	122	2.3 s
396	—	Qwen3 4B (Reasoning)OpenAlibaba	8.4	—	—	—
397	—	LFM2.5-8B-A1BOpenLiquid AI	8.3	$0.000	338	5.2 s
398	—	Claude 3.5 Sonnet (June '24)ClosedAnthropic	8.3	$6.0	—	—
399	—	Qwen3 8B (Reasoning)OpenAlibaba	8.3	$0.66	39	3.9 s
400	—	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	8.3	—	—	—
401	—	GPT-4o (ChatGPT)ClosedOpenAI	8.2	—	—	—
402	—	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
403	—	Pixtral LargeOpenMistral	8.1	$3.0	—	—
404	—	Olmo 3.1 32B ThinkOpenAllen Institute for AI	8.1	$0.000	—	—
405	—	Grok 2 (Dec '24)OpenSpaceXAI	8.0	—	—	—
406	—	GPT-5 nano (minimal)ClosedOpenAI	8.0	$0.14	157	0.8 s
407	—	Gemini 1.5 Flash (Sep '24)ClosedGoogle	8.0	—	—	—
408	—	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
409	—	GPT-4 TurboClosedOpenAI	7.9	$15	32	2.8 s
410	—	Solar Pro 2 (Non-reasoning)ClosedUpstage	7.8	—	—	—
411	—	Nova ProClosedAmazon	7.7	$1.4	—	—
412	—	Command AOpenCohere	7.7	$4.4	57	1.6 s
413	—	Qwen3.5 2B (Reasoning)OpenAlibaba	7.6	—	—	—
414	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	7.6	$1.2	300	5.5 s
415	—	Llama 3.1 Instruct 8BOpenMeta	7.6	$0.080	155	0.9 s
416	—	Grok BetaClosedSpaceXAI	7.5	—	—	—
417	—	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
418	—	Gemma 3 27B InstructOpenGoogle	7.4	$0.000	—	—
419	—	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	7.4	$0.088	115	0.5 s
420	—	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	7.4	$0.086	154	1.7 s
421	—	Mistral Large 2 (Jul '24)OpenMistral	7.3	$3.0	—	—
422	—	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
423	—	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
424	—	Qwen3 14B (Non-reasoning)OpenAlibaba	7.0	$0.61	63	2.8 s
425	—	GPT-4ClosedOpenAI	7.0	$38	—	—
426	—	GLM-4.5V (Non-reasoning)OpenZ AI	7.0	$0.90	64	20 s
427	—	Mistral Small 3OpenMistral	6.9	$0.15	151	0.7 s
428	—	Gemini 2.5 Flash-Lite (Non-reasoning)ClosedGoogle	6.9	$0.18	214	0.4 s
429	—	Nova LiteClosedAmazon	6.9	$0.11	181	1.0 s
430	—	GPT-4o miniClosedOpenAI	6.9	$0.26	67	0.9 s
431	—	Hermes 4 - Llama-3.1 70B (Non-reasoning)OpenNous Research	6.9	$0.20	97	1.3 s
432	—	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	6.8	$0.35	102	2.3 s
433	—	Ministral 3 3BOpenMistral	6.8	$0.10	163	0.6 s
434	—	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	6.8	—	—	—
435	—	Qwen3 4B (Non-reasoning)OpenAlibaba	6.8	—	—	—
436	—	Llama 3.1 Instruct 70BOpenMeta	6.8	$0.56	33	1.8 s
437	—	Granite 4.1 8BOpenIBM	6.7	$0.063	121	0.8 s
438	—	Sarvam 30B (high)OpenSarvam	6.6	$0.047	164	1.9 s
439	—	Gemini 2.0 Flash Thinking Experimental (Dec '24)ClosedGoogle	6.6	—	—	—
440	—	DeepSeek-V2.5OpenDeepSeek	6.6	—	—	—
441	—	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
442	—	Mistral SabaClosedMistral	6.4	—	—	—
443	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
444	—	Gemma 4 E2B (Non-reasoning)OpenGoogle	6.4	—	—	—
445	—	Olmo 3 32B ThinkOpenAllen Institute for AI	6.4	—	—	—
446	—	Gemini 1.5 Pro (May '24)ClosedGoogle	6.3	—	—	—
447	—	R1 1776OpenPerplexity	6.3	—	—	—
448	—	Qwen2.5 TurboClosedAlibaba	6.3	$0.088	105	2.2 s
449	—	Reka Flash (Sep '24)ClosedReka AI	6.3	$0.35	57	2.5 s
450	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.2	$1.4	60	1.2 s
450	—	Solar MiniOpenUpstage	6.2	$0.15	—	—
452	—	Grok-1OpenSpaceXAI	6.0	—	—	—
453	—	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
454	—	Phi-4 Mini InstructOpenMicrosoft	6.0	$0.000	45	0.8 s
455	—	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	6.0	—	—	—
456	—	Qwen3.5 2B (Non-reasoning)OpenAlibaba	5.6	—	—	—
457	—	Gemini 1.5 Flash-8BClosedGoogle	5.5	—	—	—
458	—	Gemma 3 12B InstructOpenGoogle	5.5	$0.000	—	—
459	—	Qwen3.5 0.8B (Reasoning)OpenAlibaba	5.5	—	—	—
460	—	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	5.3	—	—	—
461	—	Jamba 1.7 LargeOpenAI21 Labs	5.3	$3.5	57	1.4 s
462	—	Granite 4.0 H SmallOpenIBM	5.2	$0.11	386	11 s
463	—	Jamba 1.5 LargeOpenAI21 Labs	5.1	$3.5	—	—
464	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	94	2.0 s
465	—	Hermes 3 - Llama-3.1 70BOpenNous Research	5.1	$0.70	34	1.9 s
466	—	Qwen3 8B (Non-reasoning)OpenAlibaba	5.1	$0.31	39	3.8 s
467	—	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
468	—	OLMo 2 32BOpenAllen Institute for AI	5.0	—	—	—
469	—	Jamba 1.6 LargeOpenAI21 Labs	5.0	$3.5	58	1.4 s
470	—	LFM2 24B A2BOpenLiquid AI	4.9	$0.053	—	—
471	—	Gemini 1.5 Flash (May '24)ClosedGoogle	4.9	—	—	—
472	—	Phi-4OpenMicrosoft	4.9	$0.22	25	2.2 s
473	—	Claude 3 SonnetClosedAnthropic	4.7	$6.0	—	—
474	—	Nova MicroClosedAmazon	4.7	$0.061	290	1.1 s
475	—	Granite 4.1 3BOpenIBM	4.7	—	—	—
476	—	Mistral Small (Sep '24)OpenMistral	4.7	$0.30	159	0.8 s
477	—	Gemini 1.0 UltraClosedGoogle	4.6	—	—	—
478	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft	4.6	—	—	—
479	—	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	4.6	$0.30	217	1.1 s
480	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	4.6	—	—	—
481	—	Phi-4 Multimodal InstructOpenMicrosoft	4.5	$0.000	18	0.8 s
482	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
483	—	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	4.4	—	—	—
484	—	Mistral Large (Feb '24)ClosedMistral	4.4	$6.0	—	—
485	—	Mixtral 8x22B InstructOpenMistral	4.4	—	—	—
486	—	Llama 2 Chat 7BOpenMeta	4.3	$0.10	—	—
487	—	Llama 3.2 Instruct 3BOpenMeta	4.2	$0.15	52	1.1 s
488	—	MiniCPM-V 4.6 1.3BOpenOpenBMB	4.2	—	—	—
489	—	Jamba Reasoning 3BOpenAI21 Labs	4.1	—	—	—
490	—	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
491	—	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
492	—	Reka Flash 3OpenReka AI	4.1	$0.35	—	—
493	—	Olmo 3 7B ThinkOpenAllen Institute for AI	4.0	—	—	—
494	—	Claude 2.1ClosedAnthropic	3.9	—	—	—
495	—	Claude 3 HaikuClosedAnthropic	3.9	$0.50	—	—
496	—	OLMo 2 7BOpenAllen Institute for AI	3.9	—	—	—
497	—	Molmo 7B-DOpenAllen Institute for AI	3.8	—	—	—
498	—	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
499	—	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
500	—	Claude 2.0ClosedAnthropic	3.6	—	—	—
500	—	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
502	—	Mistral Small (Feb '24)ClosedMistral	3.6	$1.5	154	0.7 s
503	—	Mistral MediumClosedMistral	3.6	$4.1	91	2.1 s
504	—	GPT-3.5 TurboClosedOpenAI	3.6	$0.75	—	—
505	—	Llama 3 Instruct 70BOpenMeta	3.5	$1.2	—	—
506	—	Arctic InstructOpenSnowflake	3.4	—	—	—
506	—	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
508	—	LFM 40BClosedLiquid AI	3.4	—	—	—
509	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	3.3	$0.35	52	0.7 s
510	—	PALM-2ClosedGoogle	3.2	—	—	—
511	—	Gemini 1.0 ProClosedGoogle	3.1	—	—	—
512	—	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
513	—	Sarvam M (Reasoning)OpenSarvam	3.0	$0.000	—	—
514	—	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
514	—	Llama 2 Chat 70BOpenMeta	3.0	—	—	—
516	—	Llama 2 Chat 13BOpenMeta	3.0	—	—	—
517	—	Command-R+ (Apr '24)OpenCohere	3.0	$6.0	—	—
518	—	OpenChat 3.5 (1210)OpenOpenChat	3.0	—	—	—
519	—	DBRX InstructOpenDatabricks	3.0	—	—	—
520	—	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	2.9	—	—	—
521	—	Olmo 3 7B InstructOpenAllen Institute for AI	2.8	$0.13	—	—
522	—	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	2.8	—	—	—
523	—	LFM2.5-1.2B-ThinkingOpenLiquid AI	2.7	—	—	—
524	—	Jamba 1.7 MiniOpenAI21 Labs	2.7	—	—	—
525	—	LFM2 2.6BOpenLiquid AI	2.7	—	—	—
526	—	LFM2.5-1.2B-InstructOpenLiquid AI	2.7	—	—	—
527	—	Jamba 1.5 MiniOpenAI21 Labs	2.7	$0.25	—	—
528	—	Granite 4.0 H 1BOpenIBM	2.7	—	—	—
529	—	Qwen3 1.7B (Reasoning)OpenAlibaba	2.6	—	—	—
530	—	Jamba 1.6 MiniOpenAI21 Labs	2.6	$0.25	182	0.9 s
531	—	Mixtral 8x7B InstructOpenMistral	2.4	$0.51	—	—
532	—	Gemma 3 270MOpenGoogle	2.4	—	—	—
533	—	Apertus 70B InstructOpenSwiss AI Initiative	2.4	$1.3	—	—
534	—	Granite 4.0 MicroOpenIBM	2.4	—	—	—
535	—	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	2.3	—	—	—
536	—	Claude InstantClosedAnthropic	2.1	—	—	—
536	—	Command-R (Mar '24)OpenCohere	2.1	$0.75	—	—
536	—	Llama 65BOpenMeta	2.1	—	—	—
536	—	Mistral 7B InstructOpenMistral	2.1	$0.25	81	0.8 s
536	—	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
541	—	Granite 4.0 1BOpenIBM	2.1	—	—	—
542	—	Molmo2-8BOpenAllen Institute for AI	2.0	—	—	—
543	—	LFM2 8B A1BOpenLiquid AI	1.8	—	—	—
544	—	Granite 3.3 8B (Non-reasoning)OpenIBM	1.8	$0.085	326	26 s
545	—	Qwen3 1.7B (Non-reasoning)OpenAlibaba	1.5	—	—	—
546	—	Qwen3 0.6B (Reasoning)OpenAlibaba	1.3	—	—	—
547	—	Llama 3 Instruct 8BOpenMeta	1.2	$0.070	—	—
548	—	Gemma 3n E4B InstructOpenGoogle	1.2	$0.025	57	1.2 s
549	—	LFM2 1.2BOpenLiquid AI	1.1	—	—	—
550	—	Gemma 3 4B InstructOpenGoogle	1.1	$0.000	—	—
551	—	Llama 3.2 Instruct 1BOpenMeta	1.1	$0.050	85	0.9 s
552	—	LFM2.5-VL-1.6BOpenLiquid AI	1.0	$0.000	438	11 s
553	—	Apertus 8B InstructOpenSwiss AI Initiative	1.0	$0.13	—	—
553	—	Gemma 3 1B InstructOpenGoogle	1.0	$0.000	—	—
553	—	Gemma 3n E2B InstructOpenGoogle	1.0	$0.000	—	—
553	—	Granite 4.0 350MOpenIBM	1.0	—	—	—
553	—	Granite 4.0 H 350MOpenIBM	1.0	—	—	—
553	—	Qwen3 0.6B (Non-reasoning)OpenAlibaba	1.0	—	—	—
553	—	Tiny Aya GlobalOpenCohere	1.0	$0.000	—	—

509 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