AI Reasoning Benchmark

How do reasoning models stack up against standard LLMs? This benchmark compares 324 reasoning models against 116 standard models on composite score, pricing, and capabilities - helping you decide when chain-of-thought thinking is worth the trade-off.

Reasoning vs Standard - Head-to-Head

Reasoning Models

324

Models

Top Score

Avg Score

$10.77

Avg $/1M Out

Standard Models

116

Models

Top Score

Avg Score

$3.23

Avg $/1M Out

Reasoning models from 45 providers. Score difference: +9 points average for reasoning models.

Reasoning Models - Ranked by Score

#	Model	Provider	Score	Context	$/1M Out
1	Claude Fable 5.1Anthropic	Anthropic	96	1M	$50.00
2	Claude Fable 5.1 (batch)Anthropic	Anthropic	96	1M	$25.00
3	Claude Fable 5Anthropic	Anthropic	96	1M	$50.00
4	Claude Fable 5 (batch)Anthropic	Anthropic	96	1M	$25.00
5	Claude Opus 5.5Anthropic	Anthropic	95	1M	$20.00
6	Claude Opus 5Anthropic	Anthropic	95	1M	$25.00
7	Claude Opus 4.8Anthropic	Anthropic	95	1M	$25.00
8	Claude Opus 4.7Anthropic	Anthropic	95	1M	$25.00
9	Claude Opus 4.7 (batch)Anthropic	Anthropic	95	1M	$12.50
10	Claude Opus 4.8 (batch)Anthropic	Anthropic	95	1M	$12.50
11	GPT-5.5 ProOpenAI	OpenAI	93	1.1M	$180.00
12	GPT-5.5 Pro (batch)OpenAI	OpenAI	93	1.1M	$90.00
13	GPT-5.5OpenAI	OpenAI	93	1.1M	$30.00
14	GPT-5.5 (batch)OpenAI	OpenAI	93	1.1M	$15.00
15	Gemini 3.1 Pro Preview Custom ToolsGoogle	Google	92	1.0M	$12.00
16	Gemini 3.1 Pro PreviewGoogle	Google	92	1.0M	$12.00
17	Gemini 3.1 Pro Preview (batch)Google	Google	92	1.0M	$6.00
18	GPT-5.4 ProOpenAI	OpenAI	92	1.1M	$180.00
19	GPT-5.4 Pro (batch)OpenAI	OpenAI	92	1.1M	$90.00
20	GPT-5.4OpenAI	OpenAI	92	1.1M	$15.00
21	GPT-5.4 (batch)OpenAI	OpenAI	92	1.1M	$7.50
22	GPT-5.3-CodexOpenAI	OpenAI	91	400K	$14.00
23	GPT-5.2-CodexOpenAI	OpenAI	91	400K	$14.00
24	GPT-5.2 ProOpenAI	OpenAI	91	400K	$168.00
25	GPT-5.2 Pro (batch)OpenAI	OpenAI	91	400K	$84.00
26	GPT-5.2OpenAI	OpenAI	91	400K	$14.00
27	GPT-5.2 (batch)OpenAI	OpenAI	91	400K	$7.00
28	Claude Opus 4.6Anthropic	Anthropic	90	1M	$25.00
29	Claude Opus 4.6 (batch)Anthropic	Anthropic	90	1M	$12.50
30	GPT-5.6 Luna ProOpenAI	OpenAI	89	1.1M	$1.20
31	GPT-5.6 Luna Pro (batch)OpenAI	OpenAI	89	1.1M	$0.60
32	GPT-5.6 LunaOpenAI	OpenAI	89	1.1M	$1.20
33	GPT-5.6 Luna (batch)OpenAI	OpenAI	89	1.1M	$0.60
34	GPT-5.6 Terra ProOpenAI	OpenAI	89	1.1M	$12.00
35	GPT-5.6 Terra Pro (batch)OpenAI	OpenAI	89	1.1M	$6.00
36	GPT-5.6 TerraOpenAI	OpenAI	89	1.1M	$12.00
37	GPT-5.6 Terra (batch)OpenAI	OpenAI	89	1.1M	$6.00
38	GPT-5.6 Sol ProOpenAI	OpenAI	89	1.1M	$10.00
39	GPT-5.6 Sol Pro (batch)OpenAI	OpenAI	89	1.1M	$5.00
40	GPT-5.6 SolOpenAI	OpenAI	89	1.1M	$10.00
41	GPT-5.6 Sol (batch)OpenAI	OpenAI	89	1.1M	$5.00
42	Grok 4.7xAI	xAI	89	500K	$4.80
43	Grok 4.6xAI	xAI	89	500K	$6.00
44	Grok 4.5xAI	xAI	89	500K	$6.00
45	Grok 4.3xAI	xAI	89	1M	$2.50
46	Grok 4.20xAI	xAI	89	2M	$2.50
47	GPT-5.1-Codex-MaxOpenAI	OpenAI	89	400K	$10.00
48	GPT-5.1OpenAI	OpenAI	89	400K	$10.00
49	GPT-5.1-CodexOpenAI	OpenAI	89	400K	$10.00
50	GPT-5 ProOpenAI	OpenAI	89	400K	$120.00
51	GPT-5 Pro (batch)OpenAI	OpenAI	89	400K	$60.00
52	GPT-5OpenAI	OpenAI	89	400K	$10.00
53	GPT-5 (batch)OpenAI	OpenAI	89	400K	$5.00
54	Gemini 3 Flash PreviewGoogle	Google	88	1.0M	$3.00
55	Gemini 3 Flash Preview (batch)Google	Google	88	1.0M	$1.50
56	Grok 4.20 Multi-AgentxAI	xAI	88	2M	$2.50
57	GPT-5.1 (batch)OpenAI	OpenAI	88	400K	$5.00
58	GPT-5.1-Codex-MiniOpenAI	OpenAI	88	400K	$2.00
59	o3 ProOpenAI	OpenAI	87	200K	$80.00
60	o3OpenAI	OpenAI	87	200K	$8.00
61	o3 (batch)OpenAI	OpenAI	87	200K	$4.00
62	Claude Sonnet 5Anthropic	Anthropic	85	1M	$10.00
63	Claude Sonnet 4.6Anthropic	Anthropic	85	1M	$15.00
64	Claude Sonnet 4.6 (batch)Anthropic	Anthropic	85	1M	$7.50
65	Claude Opus 4.5Anthropic	Anthropic	85	200K	$25.00
66	Claude Opus 4.5 (batch)Anthropic	Anthropic	85	200K	$12.50
67	Gemini 2.5 ProGoogle	Google	84	1.0M	$10.00
68	Gemini 2.5 Pro (batch)Google	Google	84	1.0M	$5.00
69	Gemini 2.5 Pro Preview 06-05Google	Google	84	1.0M	$10.00
70	DeepSeek V3.2DeepSeek	DeepSeek	83	164K	$0.40
71	Claude Sonnet 4.5Anthropic	Anthropic	82	1M	$15.00
72	Claude Sonnet 4.5 (batch)Anthropic	Anthropic	82	1M	$7.50
73	GPT-6 AstraOpenAI	OpenAI	82	1.1M	$50.00
74	GPT-6 Astra (batch)OpenAI	OpenAI	82	1.1M	$25.00
75	GPT-6 Astra ProOpenAI	OpenAI	82	1.1M	$50.00
76	GPT-6 Astra Pro (batch)OpenAI	OpenAI	82	1.1M	$25.00
77	o4 MiniOpenAI	OpenAI	81	200K	$4.40
78	o4 Mini (batch)OpenAI	OpenAI	81	200K	$2.20
79	Gemini 3.8 FlashGoogle	Google	81	1.0M	$3.75
80	Gemini 3.8 Flash (batch)Google	Google	81	1.0M	$1.88
81	Grok 4.3 (batch)xAI	xAI	81	1M	$2.00
82	Muse Spark 1.3meta	meta	81	1.0M	$4.25
83	Muse Spark 1.2meta	meta	81	1.0M	$4.25
84	Muse Spark 1.1meta	meta	81	1.0M	$4.25
85	Gemma 4 31BGoogle	Google	81	262K	$0.34
86	Gemma 4 31B (free)Google	Google	81	262K	Free
87	Qwen3.5 397B A17BAlibaba	Alibaba	79	262K	$3.50
88	R1 0528DeepSeek	DeepSeek	79	164K	$2.15
89	GPT-5.4 NanoOpenAI	OpenAI	79	400K	$1.25
90	GPT-5.4 Nano (batch)OpenAI	OpenAI	79	400K	$0.63
91	GPT-5.4 MiniOpenAI	OpenAI	79	400K	$4.50
92	GPT-5.4 Mini (batch)OpenAI	OpenAI	79	400K	$2.25
93	Gemini 3.1 Flash Lite PreviewGoogle	Google	79	1.0M	$1.50
94	Gemini 2.5 Flash LiteGoogle	Google	79	1.0M	$0.40
95	Gemini 2.5 Flash Lite (batch)Google	Google	79	1.0M	$0.20
96	Gemini 2.5 FlashGoogle	Google	79	1.0M	$2.50
97	Gemini 2.5 Flash (batch)Google	Google	79	1.0M	$1.25
98	Gemini 3.5 FlashGoogle	Google	79	1.0M	$9.00
99	Gemini 3.5 Flash (batch)Google	Google	79	1.0M	$4.50
100	GLM 5.3Zhipu AI	Zhipu AI	79	1.3M	$2.64
101	GLM 5.3 (batch)Zhipu AI	Zhipu AI	79	1.0M	$2.40
102	GLM 5.2Zhipu AI	Zhipu AI	79	1.0M	$2.04
103	GLM 5.3 FlashZhipu AI	Zhipu AI	78	1.3M	$0.50
104	GLM 5.1Zhipu AI	Zhipu AI	78	205K	$3.04
105	GLM 5 TurboZhipu AI	Zhipu AI	78	203K	$4.00
106	GLM 5Zhipu AI	Zhipu AI	78	205K	$1.92
107	GLM 5.3 FlashXZhipu AI	Zhipu AI	78	1.0M	$1.25
108	GLM 5.3 Flash (batch)Zhipu AI	Zhipu AI	78	1.0M	$0.20
109	Qwen3.5-122B-A10BAlibaba	Alibaba	78	262K	$2.08
110	Qwen3.5-27BAlibaba	Alibaba	77	262K	$1.56
111	GPT-5 Mini (batch)OpenAI	OpenAI	77	400K	$1.00
112	GPT-5 Nano (batch)OpenAI	OpenAI	77	400K	$0.20
113	Gemini 3.5 Flash LiteGoogle	Google	77	1.0M	$2.50
114	Gemini 3.5 Flash Lite (batch)Google	Google	77	1.0M	$1.25
115	MiMo-V2.6-ProXiaomi	Xiaomi	76	1.0M	$0.87
116	MiMo-V2.5-ProXiaomi	Xiaomi	76	1.1M	$0.87
117	Qwen3.5-35B-A3BAlibaba	Alibaba	76	262K	$1.25
118	GLM 5.2 (free)Zhipu AI	Zhipu AI	76	33K	Free
119	Kimi K2.6Moonshot AI	Moonshot AI	76	262K	$4.00
120	Qwen3.8 Max (0902)Alibaba	Alibaba	76	1M	$6.00
121	Qwen3.7 PlusAlibaba	Alibaba	76	1M	$1.28
122	o3 MiniOpenAI	OpenAI	75	200K	$4.40
123	Claude Opus 4.1 (batch)Anthropic	Anthropic	75	200K	$37.50
124	GLM 4.7Zhipu AI	Zhipu AI	75	205K	$1.75
125	GLM 4.6Zhipu AI	Zhipu AI	75	205K	$1.75
126	GLM 4.5Zhipu AI	Zhipu AI	75	131K	$2.20
127	Qwen3.7 MaxAlibaba	Alibaba	75	1M	$4.42
128	Qwen3.5 Plus 2026-04-20Alibaba	Alibaba	75	1M	$1.80
129	Qwen3.6 Max PreviewAlibaba	Alibaba	75	262K	$6.16
130	Hy3Tencent	Tencent	74	262K	$0.53
131	Claude Opus 4.1Anthropic	Anthropic	74	200K	$75.00
132	o1OpenAI	OpenAI	74	200K	$60.00
133	o3 Mini (batch)OpenAI	OpenAI	74	200K	$2.20
134	Qwen3.6 PlusAlibaba	Alibaba	74	1M	$1.95
135	MiniMax M3MiniMax	MiniMax	74	1.0M	$1.20
136	Claude Sonnet 4Anthropic	Anthropic	74	200K	$15.00
137	R1DeepSeek	DeepSeek	74	64K	$2.50
138	o1-proOpenAI	OpenAI	74	200K	$600.00
139	Qwen3.8 27BAlibaba	Alibaba	73	1M	$3.00
140	MiMo-V2.5Xiaomi	Xiaomi	73	1.1M	$0.28
141	Gemma 4 26B A4B Google	Google	73	262K	$0.30
142	Gemma 4 26B A4B (free)Google	Google	73	262K	Free
143	Qwen3.8 27B (free)Alibaba	Alibaba	73	262K	Free
144	Inklingthinkingmachines	thinkingmachines	73	1.0M	$4.05
145	Inkling (free)thinkingmachines	thinkingmachines	73	1.0M	Free
146	GLM 5V TurboZhipu AI	Zhipu AI	72	203K	$4.00
147	o4 Mini HighOpenAI	OpenAI	72	200K	$4.40
148	DeepSeek V3.2 ExpDeepSeek	DeepSeek	72	164K	$0.41
149	DeepSeek V3.1DeepSeek	DeepSeek	72	164K	$0.95
150	Mistral Medium 3.5Mistral AI	Mistral AI	72	262K	$7.50
151	MiniMax M2.7MiniMax	MiniMax	72	205K	$1.20
152	MiniMax M2.5MiniMax	MiniMax	72	205K	$1.08
153	MiniMax M2.1MiniMax	MiniMax	71	205K	$1.20
154	MiniMax M2MiniMax	MiniMax	71	205K	$1.02
155	MiniMax M1MiniMax	MiniMax	71	1M	$2.20
156	GLM 4.5 AirZhipu AI	Zhipu AI	71	131K	$0.85
157	Claude Haiku 4.5Anthropic	Anthropic	70	200K	$5.00
158	Claude Haiku 4.5 (batch)Anthropic	Anthropic	70	200K	$2.50
159	Qwen3 VL 235B A22B ThinkingAlibaba	Alibaba	69	131K	$4.00
160	DeepSeek V3.1 TerminusDeepSeek	DeepSeek	69	164K	$1.00
161	Inkling Smallthinkingmachines	thinkingmachines	69	1.0M	$1.20
162	Inkling Small (free)thinkingmachines	thinkingmachines	69	1.0M	Free
163	Qwen3.5-FlashAlibaba	Alibaba	69	1M	$0.26
164	Hy3 previewTencent	Tencent	68	262K	$0.60
165	Qwen3.5 Plus 2026-02-15Alibaba	Alibaba	68	1M	$1.56
166	Qwen3 Max ThinkingAlibaba	Alibaba	68	262K	$3.90
167	Qwen3 Next 80B A3B ThinkingAlibaba	Alibaba	67	262K	$1.20
168	Qwen3.5-9BAlibaba	Alibaba	67	262K	$0.15
169	Step 3.5 FlashStepFun	StepFun	66	262K	$0.30
170	Composer 2Cursor	Cursor	66	200K	$2.50
171	Composer 2 FastCursor	Cursor	66	200K	$7.50
172	GLM 4.6VZhipu AI	Zhipu AI	66	131K	$0.90
173	Qwen3 235B A22B Thinking 2507Alibaba	Alibaba	65	131K	$2.30
174	Qwen3 30B A3B Thinking 2507Alibaba	Alibaba	64	82K	$2.40
175	Qwen3 30B A3BAlibaba	Alibaba	64	131K	$0.50
176	o3 Mini HighOpenAI	OpenAI	64	200K	$4.40
177	GLM 4.7 FlashZhipu AI	Zhipu AI	64	200K	$0.40
178	Trinity Large Thinkingarcee-ai	arcee-ai	63	262K	$0.80
179	GLM 4.5VZhipu AI	Zhipu AI	62	66K	$1.80
180	GPT-5 NanoOpenAI	OpenAI	62	400K	$0.40
181	gpt-oss-120bOpenAI	OpenAI	62	131K	$0.60
182	Mercury 2.5Inception	Inception	61	260K	$0.15
183	Qwen3 8BAlibaba	Alibaba	61	131K	$0.45
184	Mercury 2Inception	Inception	61	128K	$0.75
185	Nova 2 LiteAmazon	Amazon	60	1M	$2.50
186	gpt-oss-20bOpenAI	OpenAI	57	131K	$0.09
187	gpt-oss-20b (batch)OpenAI	OpenAI	57	131K	$0.11
188	Qwen3 235B A22BAlibaba	Alibaba	54	131K	$1.82
189	Granite 4.2 8BIBM	IBM	54	131K	$0.25
190	GPT-5 MiniOpenAI	OpenAI	54	400K	$2.00
191	Command A+Cohere	Cohere	51	192K	$1.50
192	Kimi K2.5Moonshot AI	Moonshot AI	48	262K	$2.25
193	R1 Distill Llama 70BDeepSeek	DeepSeek	41	8K	$0.80
194	GPT-6 Luna ProOpenAI	OpenAI	40	1.1M	$0.50
195	GPT-6 Luna Pro (batch)OpenAI	OpenAI	40	1.1M	$0.25
196	GPT-6 LunaOpenAI	OpenAI	40	1.1M	$0.50
197	GPT-6 Luna (batch)OpenAI	OpenAI	40	1.1M	$0.25
198	GPT-6 Sol ProOpenAI	OpenAI	40	1.1M	$10.00
199	GPT-6 Sol Pro (batch)OpenAI	OpenAI	40	1.1M	$5.00
200	GPT-6 SolOpenAI	OpenAI	40	1.1M	$10.00
201	GPT-6 Sol (batch)OpenAI	OpenAI	40	1.1M	$5.00
202	Claude Opus 5.5 (batch)Anthropic	Anthropic	40	1M	$10.00
203	MiMo-V2.6-Pro-UltraSpeedXiaomi	Xiaomi	40	1.0M	$8.70
204	MiMo-V2.6-FlashXiaomi	Xiaomi	40	1.0M	$0.28
205	Qwen3.8 Omni FlashAlibaba	Alibaba	40	1M	$0.47
206	Ternary Bonsai 2 27Bprism-ml	prism-ml	40	262K	$0.50
207	DeepSeek Pro Latest~deepseek	~deepseek	40	1.0M	$4.30
208	DeepSeek Flash Latest~deepseek	~deepseek	40	1.0M	$0.50
209	GPT Astra Latest~openai	~openai	40	1.1M	$50.00
210	GPT Sol Latest~openai	~openai	40	1.1M	$10.00
211	GPT Terra Latest~openai	~openai	40	1.1M	$12.00
212	GPT Luna Latest~openai	~openai	40	1.1M	$0.50
213	Fugu Ultra v2sakana	sakana	40	1M	$30.00
214	Fugu Maxsakana	sakana	40	1M	$6.00
215	Ling 3.0 Flash VLinclusionai	inclusionai	40	131K	$0.18
216	Ling 3.0 Flash VL (free)inclusionai	inclusionai	40	262K	Free
217	DeepSeek V4.1 FlashDeepSeek	DeepSeek	40	1.0M	$0.50
218	DeepSeek V4.1 Flash (batch)DeepSeek	DeepSeek	40	1.0M	$0.34
219	Ling 3.0 Flash Sante (free)inclusionai	inclusionai	40	262K	Free
220	Muse Spark 1.3 Contributormeta	meta	40	1.0M	$0.20
221	Hy4 previewTencent	Tencent	40	1.0M	$2.50
222	Ling 3.0 Flash Fininclusionai	inclusionai	40	262K	$0.18
223	Ling 3.0 Flash Fin (free)inclusionai	inclusionai	40	262K	Free
224	GLM Flash Latest~z-ai	~z-ai	40	1.3M	$0.25
225	Qwen3.8 FlashAlibaba	Alibaba	40	1M	$0.47
226	Muse Spark 1.2 Contributormeta	meta	40	1.0M	$0.20
227	DeepSeek V4 Flash Vision ExpDeepSeek	DeepSeek	40	1.0M	$0.66
228	GLM Latest~z-ai	~z-ai	40	1.3M	$2.50
229	Dots3-Note Preview (free)dots-studio	dots-studio	40	512K	Free
230	Gemini 3.7 FlashGoogle	Google	40	1.0M	$3.75
231	Gemini 3.7 Flash (batch)Google	Google	40	1.0M	$1.88
232	Seed 2.1 TurboByteDance	ByteDance	40	262K	$2.50
233	Qwen3.8 2.4T A95BAlibaba	Alibaba	40	1.0M	$6.00
234	Seed-2.0-CodeByteDance	ByteDance	40	262K	$3.00
235	DeepSeek V4 Pro 0813DeepSeek	DeepSeek	40	1.0M	$1.98
236	LFM2.5-2.6B (free)Liquid AI	Liquid AI	40	66K	Free
237	Nemotron 3.5 LightningNVIDIA	NVIDIA	40	262K	$0.20
238	Nemotron 3.5 Lightning (free)NVIDIA	NVIDIA	40	1M	Free
239	Sakana Namazusakana	sakana	40	262K	$4.00
240	Solar Pro 4Upstage	Upstage	40	524K	$0.36
241	Muse Glimmer 30Bmeta	meta	40	131K	$1.20
242	DeepSeek V4 Flash Latest~deepseek	~deepseek	40	1.3M	$0.80
243	DeepSeek V4 Flash 0731DeepSeek	DeepSeek	40	1.3M	$0.64
244	Qwen3.7 FlashAlibaba	Alibaba	40	1M	$0.13
245	Claude Opus 5 (batch)Anthropic	Anthropic	40	1M	$12.50
246	Ling 3.0 Flashinclusionai	inclusionai	40	262K	$0.06
247	Laguna S 2.1poolside	poolside	40	1.0M	$0.18
248	Laguna S 2.1 (free)poolside	poolside	40	262K	Free
249	Gemini 3.6 FlashGoogle	Google	40	1.0M	$3.75
250	Gemini 3.6 Flash (batch)Google	Google	40	1.0M	$1.88
251	LongCat 2.0Meituan	Meituan	40	1.0M	$1.20
252	Kimi K3Moonshot AI	Moonshot AI	40	1.0M	$15.00
253	Kimi K3 (batch)Moonshot AI	Moonshot AI	40	1.0M	$11.40
254	Grok Latest~x-ai	~x-ai	-	500K	$4.80
255	Aion-3.0-Miniaion-labs	aion-labs	-	131K	$1.40
256	Aion-3.0aion-labs	aion-labs	-	131K	$6.00
257	Laguna XS 2.1poolside	poolside	-	262K	$0.12
258	Laguna XS 2.1 (free)poolside	poolside	-	262K	Free
259	Claude Sonnet 5 (batch)Anthropic	Anthropic	-	1M	$5.00
260	Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google	Google	-	66K	$1.50
261	Fugu Ultrasakana	sakana	-	1M	$30.00
262	Nano Banana 2 (Gemini 3.1 Flash Image)Google	Google	-	131K	$3.00
263	Nano Banana Pro (Gemini 3 Pro Image)Google	Google	-	131K	$12.00
264	North Mini Code (free)Cohere	Cohere	-	256K	Free
265	Kimi K2.7 CodeMoonshot AI	Moonshot AI	-	262K	$3.30
266	Claude Fable Latest~anthropic	~anthropic	-	1M	$50.00
267	Nemotron 3.5 Content SafetyNVIDIA	NVIDIA	-	131K	$0.20
268	Nemotron 3.5 Content Safety (free)NVIDIA	NVIDIA	-	128K	Free
269	Nemotron 3 UltraNVIDIA	NVIDIA	-	262K	$2.40
270	Nemotron 3 Ultra (free)NVIDIA	NVIDIA	-	1M	Free
271	Step 3.7 FlashStepFun	StepFun	-	262K	$1.15
272	Grok Build 0.1xAI	xAI	-	256K	$2.00
273	Perceptron Mk1perceptron	perceptron	-	33K	$1.50
274	Gemini 3.1 Flash LiteGoogle	Google	-	1.0M	$1.50
275	Gemini 3.1 Flash Lite (batch)Google	Google	-	1.0M	$0.75
276	Mistral Medium 3.5 (batch)Mistral AI	Mistral AI	-	262K	$3.75
277	Nemotron 3 Nano Omni (free)NVIDIA	NVIDIA	-	256K	Free
278	Claude Haiku Latest~anthropic	~anthropic	-	200K	$5.00
279	GPT Mini Latest~openai	~openai	-	400K	$4.50
280	Gemini Pro Latest~google	~google	-	1.0M	$12.00
281	Kimi Latest~moonshotai	~moonshotai	-	1.0M	$14.33
282	Gemini Flash Latest~google	~google	-	1.0M	$3.75
283	Claude Sonnet Latest~anthropic	~anthropic	-	1M	$10.00
284	Qwen3.6 FlashAlibaba	Alibaba	-	1M	$1.13
285	Qwen3.6 35B A3BAlibaba	Alibaba	-	262K	$1.00
286	Qwen3.6 27BAlibaba	Alibaba	-	262K	$2.70
287	DeepSeek V4 Pro 0423DeepSeek	DeepSeek	-	1.0M	$1.91
288	DeepSeek V4 Flash 0423DeepSeek	DeepSeek	-	1.0M	$0.18
289	GPT-5.4 Image 2OpenAI	OpenAI	-	272K	$15.00
290	Claude Opus Latest~anthropic	~anthropic	-	1M	$20.00
291	Mistral Small 4Mistral AI	Mistral AI	-	262K	$0.60
292	Mistral Small 4 (batch)Mistral AI	Mistral AI	-	262K	$0.30
293	Nemotron 3 SuperNVIDIA	NVIDIA	-	262K	$0.45
294	Nemotron 3 Super (free)NVIDIA	NVIDIA	-	262K	Free
295	Seed-2.0-LiteByteDance	ByteDance	-	262K	$2.00
296	Seed-2.0-MiniByteDance	ByteDance	-	262K	$0.40
297	Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google	Google	-	66K	$3.00
298	Aion-2.0aion-labs	aion-labs	-	131K	$1.60
299	Solar Pro 3Upstage	Upstage	-	131K	$0.60
300	Seed 1.6 FlashByteDance	ByteDance	-	262K	$0.30
301	Seed 1.6ByteDance	ByteDance	-	262K	$2.00
302	Nemotron 3 Nano 30B A3BNVIDIA	NVIDIA	-	262K	$0.20
303	Nano Banana Pro (Gemini 3 Pro Image Preview)Google	Google	-	66K	$12.00
304	Kimi K2 ThinkingMoonshot AI	Moonshot AI	-	262K	$2.50
305	Sonar Pro SearchPerplexity	Perplexity	-	200K	$15.00
306	gpt-oss-safeguard-20bOpenAI	OpenAI	-	131K	$0.30
307	GPT-5 Image MiniOpenAI	OpenAI	-	400K	$2.00
308	Qwen3 VL 8B ThinkingAlibaba	Alibaba	-	131K	$2.10
309	GPT-5 ImageOpenAI	OpenAI	-	400K	$10.00
310	Qwen3 VL 30B A3B ThinkingAlibaba	Alibaba	-	262K	$2.40
311	Hunyuan A13B InstructTencent	Tencent	-	131K	$0.57
312	ERNIE 4.5 VL 424B A47B Baidu	Baidu	-	123K	$1.25
313	Qwen3 14BAlibaba	Alibaba	-	131K	$0.24
314	Qwen3 32BAlibaba	Alibaba	-	131K	$0.28
315	Reka Flash 3rekaai	rekaai	-	66K	$0.20
316	Sonar Reasoning ProPerplexity	Perplexity	-	128K	$8.00
317	Sonar Deep ResearchPerplexity	Perplexity	-	128K	$8.00
318	SWE-1.5Windsurf	Windsurf	-	0	Free
319	Falcon-H1-Arabic 34B InstructTII	TII	-	262K	Free
320	Falcon-H1-Arabic 7B InstructTII	TII	-	262K	Free
321	Falcon-H1-Arabic 3B InstructTII	TII	-	131K	Free
322	Falcon Arabic 7B InstructTII	TII	-	33K	Free
323	Falcon3 10B InstructTII	TII	-	33K	Free
324	Falcon3 7B InstructTII	TII	-	33K	Free

Top Standard Models (Non-Reasoning) - For Comparison

#	Model	Provider	Score	Context	$/1M Out
1	GPT-5.2 ChatOpenAI	OpenAI	91	128K	$14.00
2	Gemma 2 27BGoogle	Google	77	8K	$0.65
3	GPT-4o (batch)OpenAI	OpenAI	72	128K	$5.00
4	DeepSeek V3 0324DeepSeek	DeepSeek	72	164K	$1.00
5	GPT-4o (2024-11-20)OpenAI	OpenAI	71	128K	$10.00
6	GPT-4o (2024-08-06)OpenAI	OpenAI	71	128K	$10.00
7	GPT-4oOpenAI	OpenAI	71	128K	$10.00
8	GPT-4o (2024-05-13)OpenAI	OpenAI	71	128K	$15.00
9	Llama 4 MaverickMeta	Meta	71	1.0M	$0.65
10	DeepSeek V3DeepSeek	DeepSeek	70	164K	$0.89

Understanding AI Reasoning Benchmarks

What Is Chain-of-Thought?

Chain-of-thought (CoT) prompting enables AI models to break down complex problems into intermediate steps before producing a final answer. Models like OpenAI o1 and DeepSeek R1 internalize this process, generating hidden reasoning traces that dramatically improve accuracy on math, logic, and multi-step tasks compared to direct answering.

When Reasoning Helps

Reasoning models shine on tasks that require multiple logical steps: mathematical proofs, complex coding challenges, scientific analysis, strategic planning, and any problem where standard models tend to hallucinate or skip steps. For simple Q&A or creative writing, standard models are often faster and equally effective.

Speed vs Accuracy

Reasoning models consume more tokens and take longer to respond because they generate internal thinking traces. This trade-off is worthwhile when correctness matters more than latency - for example in code generation, financial analysis, or exam-style problems. For real-time chat, standard models remain the better choice.

Emerging Reasoning Models

The reasoning model landscape is evolving rapidly. OpenAI's o1 and o3 series led the way, followed by DeepSeek R1 bringing open-source reasoning. Google, Anthropic, and other providers have since introduced their own reasoning-capable models, driving down costs and expanding access to chain-of-thought capabilities.

Reasoning Models Best for Math Best for Coding Speed Comparison Compare Models LLM Leaderboard Scores Explained Choosing Guide

Frequently Asked Questions

AI reasoning benchmarks test a model's ability to solve complex problems requiring logical thinking, mathematical reasoning, scientific analysis, and multi-step problem solving - tasks that go beyond simple pattern matching.

DeepSeek R1, OpenAI o3, and Claude with extended thinking lead on reasoning benchmarks. These models use chain-of-thought processing to break down complex problems into steps, achieving significantly higher accuracy.

Key reasoning benchmarks include GPQA Diamond (graduate-level science), MATH-500 (mathematical reasoning), AIME (competition math), ARC Challenge (science questions), and GSM8K (grade-school math). Each tests different aspects of reasoning ability.