Best AI Models for Reasoning

Q: Which AI model has the best reasoning?

Reasoning rankings shift as new models launch. The live leaderboard above shows current standings based on GPQA Diamond, ARC-AGI, and other reasoning benchmarks.

Q: What is GPQA Diamond?

GPQA Diamond is a graduate-level question answering benchmark designed to test deep reasoning. Questions are written by domain experts and verified to be answerable only with genuine understanding.

Q: How does ARC-AGI measure reasoning?

ARC-AGI tests abstract reasoning through visual pattern puzzles that require novel inference, not memorization. It is considered one of the hardest AI benchmarks.

AI models ranked by reasoning benchmarks. Compare GPQA Diamond, ARC-AGI, BBH, and other reasoning tests across all providers.

235

Models

Providers

111

Open Source

$0.60

Median $/1M in

Top 3

Claude Mythos Preview

🇺🇸 Anthropic

1.0MN/A/M in

81.814 benchmarks

Full Rankings

#	Model	Avg	ARC-AGI	ARC-AGI-2	BBH	GPQA diamond	HLE	SimpleBench	$/1M in	Context
1	GPT-5.5 Pro🇺🇸 OpenAI	87.8	-	-	-	94.2	-	-	$30.00	400K
2	GPT-5.5🇺🇸 OpenAI	85.0	95.0	-	-	93.6	-	-	$5.00	400K
3	Claude Mythos Preview🇺🇸 Anthropic	81.8	-	-	-	94.5	56.8	-	N/A	1.0M
4	GPT-6.1 Sol🇺🇸 OpenAI	77.3	98.5	94.2	-	97.8	-	-	$2.00	1.1M
5	DeepSeek-V2 (MoE-236B, May 2024)🇨🇳 DeepSeekOpen	76.5	-	-	71.7	-	-	-	N/A	0K
6	Gemini 4 Argon🇺🇸 Google DeepMind	76.5	98.5	91.3	-	99.2	-	-	$2.00	1.0M
7	GPT-6 Astra🇺🇸 OpenAI	74.7	98.5	95.0	-	98.3	52.5	-	$10.00	1.1M
8	Claude Opus 5.5🇺🇸 Anthropic	74.0	98.5	93.3	-	91.1	-	-	$4.00	1.0M
9	U PaLM 2-L Unknown	73.4	-	-	-	-	-	-	N/A	0K
10	Claude Opus 5🇺🇸 Anthropic	68.4	97.5	90.4	-	95.7	-	76.7	$5.00	1.0M
11	Claude Fable 5.1🇺🇸 Anthropic	68.2	97.5	90.0	-	-	43.8	-	$10.00	1.0M
12	Claude Sonnet 5.5🇺🇸 Anthropic	67.8	-	-	-	98.0	43.4	-	$2.00	1.0M
13	Claude Fable 5🇺🇸 Anthropic	67.6	98.5	89.2	-	84.5	-	78.3	$10.00	1.0M
14	GPT-6 Sol🇺🇸 OpenAI	67.5	95.5	89.6	-	96.3	-	-	$2.00	1.1M
15	phi-3-small 7.4B🇺🇸 MicrosoftOpen	67.4	-	-	72.1	-	-	-	N/A	0K
16	GPT-5.6 Terra🇺🇸 OpenAI	66.9	96.5	83.9	-	94.9	-	38.7	$2.00	1.1M
17	GPT-5.6 Sol🇺🇸 OpenAI	65.8	97.5	92.5	-	95.1	-	66.0	$2.00	1.1M
18	GPT-5.4 Pro🇺🇸 OpenAI	64.8	94.5	83.3	-	92.8	41.5	68.9	$30.00	1.1M
19	Muse Spark Open🇺🇸 Meta	63.6	-	-	-	88.3	-	-	$1.25	1.0M
20	U PaLM 2-M Unknown	63.0	-	-	-	-	-	-	N/A	0K
21	Qwen3.7 Max🇨🇳 Alibaba QwenOpen	62.0	-	-	-	91.5	-	64.5	$1.48	1.0M
22	DeepSeek V4 Flash🇨🇳 DeepSeekOpen	61.6	-	-	-	-	-	35.6	$0.09	1.0M
23	o3 Pro🇺🇸 OpenAI	61.3	59.3	4.9	-	-	-	-	$20.00	200K
24	Qwen-14B🇨🇳 Alibaba QwenOpen	60.7	-	-	40.0	-	-	-	N/A	0K
25	DeepSeek V4 Pro 0813🇨🇳 DeepSeek	60.4	90.5	61.3	-	92.6	-	-	$1.32	1.0M
26	Qwen3.5 397B A17B🇨🇳 Alibaba QwenOpen	60.3	-	-	-	85.2	-	-	$0.50	262K
27	Gemini 3.7 Flash🇺🇸 Google DeepMind	59.1	95.5	84.6	-	97.0	-	-	$0.75	1.0M
28	U internlm-20b Unknown	59.0	-	-	36.7	-	-	-	N/A	0K
29	U PaLM 2-S Unknown	58.9	-	-	-	-	-	-	N/A	0K
30	phi-3-medium 14B🇺🇸 MicrosoftOpen	58.6	-	-	75.2	3.6	-	-	N/A	0K
31	GPT-5.2 Pro🇺🇸 OpenAI	58.1	90.5	54.2	-	-	-	48.9	$21.00	400K
32	Gemini 3.8 Flash🇺🇸 Google DeepMind	58.0	98.5	89.2	-	97.8	41.7	-	$0.82	1.0M
33	Falcon 2 11B TIIOpen	58.0	-	-	-	-	-	-	N/A	0K
34	R1 0528🇨🇳 DeepSeekOpen	57.9	21.2	1.1	-	68.4	-	29.0	$0.50	164K
35	Mixtral 8x7B Instruct🇫🇷 Mistral AIOpen	57.8	-	-	-	7.5	-	-	$0.54	33K
36	Kimi K3🇨🇳 moonshotai	57.8	94.5	60.4	-	94.6	-	52.8	$0.24	1.0M
37	Claude Sonnet 5🇺🇸 Anthropic	57.7	-	-	-	91.0	-	52.7	$2.00	1.0M
38	Grok 4.6🇺🇸 xAI	57.5	87.5	67.1	-	95.8	-	71.1	$2.00	500K
39	Qwen3.6 27B🇨🇳 Alibaba QwenOpen	57.3	-	-	-	84.5	-	-	$0.25	262K
40	GLM 5.3🇨🇳 z-ai	56.7	-	-	-	91.5	-	-	$0.08	1.0M
41	Claude Haiku 5.5🇺🇸 Anthropic	56.5	89.0	61.3	-	89.8	26.6	-	$0.10	1.0M
42	Claude Opus 4.8🇺🇸 Anthropic	56.4	92.5	72.1	-	91.7	-	57.8	$5.00	1.0M
43	GLM 5.2🇨🇳 z-aiOpen	56.3	77.0	22.8	-	92.9	-	50.6	$0.03	1.0M
44	Grok 4.3🇺🇸 xAI	56.3	-	-	-	88.7	-	-	$1.25	1.0M
45	Gemini 3 Pro🇺🇸 Google DeepMind	56.2	75.0	31.1	-	93.9	34.4	71.7	N/A	0K
46	Kimi K2.7 Code🇨🇳 moonshotaiOpen	56.2	-	-	-	87.3	-	49.5	$0.67	262K
47	DeepSeek V3🇨🇳 DeepSeekOpen	56.2	-	-	83.3	43.8	-	2.7	$0.26	164K
48	Muse Spark🇺🇸 Meta	56.1	-	-	-	90.0	37.6	-	N/A	0K
49	Kimi K2 0711🇨🇳 moonshotaiOpen	56.1	-	-	-	-	-	11.6	$0.57	131K
50	DeepSeek V4 Flash 0731🇨🇳 DeepSeek	55.7	89.0	61.4	-	91.7	-	53.3	$0.44	1.0M
51	GPT-5.6 Luna🇺🇸 OpenAI	55.3	88.0	59.5	-	92.5	-	36.2	$0.20	1.1M
52	Qwen3.8 Max (0902)🇨🇳 Alibaba Qwen	55.3	-	-	-	94.0	-	-	$2.00	1.0M
53	GPT-4 (older v0314)🇺🇸 OpenAI	55.0	-	-	-	14.3	-	-	$30.00	8K
54	Gemini 3.5 Flash🇺🇸 Google DeepMind	54.9	92.5	72.1	-	94.2	-	72.0	$1.50	1.0M
55	GLM 5🇨🇳 z-aiOpen	54.7	44.7	4.9	-	83.8	-	43.8	$1.00	205K
56	GLM 5.1🇨🇳 z-aiOpen	54.6	-	-	-	90.1	-	46.1	$1.40	205K
57	Grok 4.5🇺🇸 xAI	54.5	87.2	52.6	-	95.0	-	64.0	$2.00	500K
58	Mixtral 8x7B🇫🇷 Mistral AIOpen	54.3	-	-	-	7.8	-	-	N/A	0K
59	Gemini 2.0 Pro🇺🇸 Google DeepMind	54.3	-	-	-	56.5	-	-	N/A	0K
60	phi-3-mini 3.8B🇺🇸 MicrosoftOpen	54.3	-	-	62.3	-	-	-	N/A	0K
61	DeepSeek V4 Pro🇨🇳 DeepSeekOpen	54.1	-	-	-	91.5	-	-	$0.96	1.0M
62	DeepSeek V4.1 Flash🇨🇳 DeepSeekOpen	54.1	94.5	72.9	-	90.0	-	-	$0.30	1.0M
63	Gemini 3.6 Flash🇺🇸 Google DeepMind	54.1	91.2	60.4	-	96.0	-	-	$0.75	1.0M
64	Grok 4🇺🇸 xAI	54.0	66.7	16.0	-	86.1	-	52.6	N/A	0K
65	Qwen3 235B A22B🇨🇳 Alibaba QwenOpen	53.7	-	-	-	60.9	-	17.2	$0.46	131K
66	Grok-3 mini🇺🇸 xAI	53.7	16.5	0.4	-	71.2	-	-	N/A	0K
67	Qwen3.6 Plus🇨🇳 Alibaba QwenOpen	53.6	-	-	-	88.0	-	-	$0.33	1.0M
68	U Nemotron-4 15B Unknown	53.4	-	-	44.9	-	-	-	N/A	0K
69	Grok 4 Fast🇺🇸 xAI	53.3	48.5	5.3	-	-	-	-	N/A	0K
70	gpt-oss-20b🇺🇸 OpenAIOpen	53.2	-	-	-	49.7	-	-	$0.02	131K
71	GPT-5🇺🇸 OpenAI	53.2	65.7	9.9	-	85.0	21.6	48.0	$1.25	400K
72	Qwen2.5 Coder 32B Instruct🇨🇳 Alibaba QwenOpen	53.1	-	-	-	-	-	-	$0.66	33K
73	Qwen3 235B A22B Thinking 2507🇨🇳 Alibaba QwenOpen	53.1	-	-	-	73.4	-	-	$0.45	128K
74	Gemma 4 31B🇺🇸 Google DeepMindOpen	53.0	-	-	-	70.5	-	-	$0.09	262K
75	Qwen3.8 27B🇨🇳 Alibaba Qwen	52.4	87.5	42.4	-	-	-	-	$0.04	1.0M
76	Qwen2.5-Coder-3B🇨🇳 Alibaba QwenOpen	52.2	-	-	-	-	-	-	N/A	0K
77	Kimi K2 Thinking🇨🇳 moonshotaiOpen	52.2	-	-	-	79.0	-	-	$0.60	262K
78	GPT-5.4🇺🇸 OpenAI	52.1	93.7	74.0	-	94.9	33.0	-	$2.50	1.1M
79	DeepSeek R1 Distill Qwen 14B🇨🇳 DeepSeekOpen	52.0	-	-	-	26.3	-	-	N/A	0K
80	Qwen3 32B🇨🇳 Alibaba QwenOpen	51.7	-	-	-	56.6	-	-	$0.08	131K
81	Qwen3.5-35B-A3B🇨🇳 Alibaba QwenOpen	51.6	-	-	-	81.2	-	-	$0.14	262K
82	GPT-5 Mini🇺🇸 OpenAI	51.5	54.3	4.4	-	69.4	15.4	-	$0.25	400K
83	o3🇺🇸 OpenAI	51.3	60.8	6.5	-	75.8	16.3	43.7	$2.00	200K
84	Claude Opus 4.7🇺🇸 Anthropic	51.2	93.5	75.8	-	90.5	33.0	54.0	$5.00	1.0M
85	GPT-4o (2024-05-13)🇺🇸 OpenAI	51.1	-	-	-	31.9	-	-	$5.00	128K
86	GPT-6 Luna🇺🇸 OpenAI	51.1	86.7	59.3	-	90.9	-	-	$0.10	1.1M
87	Qwen3.6 Max Preview🇨🇳 Alibaba QwenOpen	51.0	-	-	-	83.2	-	55.6	$1.03	262K
88	Gemini 2.5 Pro🇺🇸 Google DeepMind	50.9	41.0	4.9	-	83.7	17.7	54.9	$1.25	1.0M
89	DeepSeek-Coder-V2-Lite-Base🇨🇳 DeepSeekOpen	50.8	-	-	-	-	-	-	N/A	0K
90	DeepSeek V3.1🇨🇳 DeepSeekOpen	50.7	-	-	-	-	-	28.0	$0.25	164K
91	Grok 4.7🇺🇸 xAI	50.7	90.2	61.4	-	94.1	-	-	$2.00	500K
92	Qwen2.5 Coder 14B Instruct🇨🇳 AlibabaOpen	50.0	-	-	-	-	-	-	N/A	0K
93	MiniMax M3🇨🇳 minimaxOpen	50.0	-	-	-	91.5	-	35.0	$0.30	1.0M
94	Gemini 3 Flash Preview🇺🇸 Google DeepMind	49.8	84.7	33.6	-	89.4	-	53.3	$0.50	1.0M
95	Grok 4.20🇺🇸 xAI	49.5	89.5	65.1	-	89.3	-	-	$1.25	2.0M
96	Kimi K2.5🇨🇳 moonshotaiOpen	49.5	65.3	11.8	-	86.9	20.6	36.2	$0.50	262K
97	gpt-oss-120b🇺🇸 OpenAIOpen	49.3	-	-	-	67.7	-	6.5	$0.04	131K
98	Qwen2.5 72B Instruct🇨🇳 Alibaba QwenOpen	49.3	-	-	73.1	33.5	-	-	$0.36	33K
99	MiniMax M2.5🇨🇳 minimaxOpen	48.6	63.7	4.9	-	-	-	-	$0.27	205K
100	o4 Mini🇺🇸 OpenAI	48.6	58.7	6.1	-	75.8	13.9	26.4	$1.10	200K
101	DeepSeek V3.2🇨🇳 DeepSeekOpen	48.3	57.0	4.0	-	81.1	-	-	$0.28	164K
102	Qwen3 235B A22B Instruct 2507🇨🇳 Alibaba QwenOpen	48.3	11.0	1.3	-	-	-	-	$0.09	262K
103	Claude Opus 4.6🇺🇸 Anthropic	48.3	94.0	69.2	-	91.0	31.1	61.1	$5.00	1.0M
104	Gemini 3.1 Pro Preview🇺🇸 Google DeepMind	48.2	98.0	77.1	-	96.5	43.7	75.5	$2.00	1.0M
105	Claude 3.7 Sonnet🇺🇸 Anthropic	48.2	28.6	0.9	-	76.0	3.4	35.7	N/A	0K
106	GLM 5.3 Flash🇨🇳 z-ai	48.1	91.0	65.8	-	90.5	-	-	$0.02	1.0M
107	Gemini 2.0 Flash🇺🇸 Google DeepMind	48.0	-	1.3	-	52.2	-	17.3	$0.10	1.0M
108	Gemini 2.0 Flash (Dec 2024)🇺🇸 Google DeepMind	47.8	-	1.3	-	54.4	-	17.3	N/A	0K
109	U Stable Beluga 2 Unknown	47.8	-	-	59.1	-	-	-	N/A	0K
110	GPT-5.1🇺🇸 OpenAI	47.5	72.8	17.6	-	87.0	19.8	43.8	$1.25	400K
111	GLM 4.7🇨🇳 z-aiOpen	46.7	-	-	-	81.0	-	37.2	$0.60	205K
112	Qwen3 Max🇨🇳 Alibaba QwenOpen	46.5	-	-	-	63.5	-	-	$0.78	262K
113	Gemma 4 26B A4B 🇺🇸 Google DeepMindOpen	46.4	-	-	-	67.0	-	-	$0.08	262K
114	GPT-5.2🇺🇸 OpenAI	46.1	86.2	52.9	-	92.2	24.2	35.0	$1.75	400K
115	Claude Opus 4🇺🇸 Anthropic	46.1	35.7	8.6	-	68.3	6.2	50.6	$15.00	200K
116	Mistral Large 2411🇫🇷 Mistral AIOpen	45.8	-	-	-	35.1	-	-	$2.00	131K
117	Gemini 1.5 Flash (May 2024)🇺🇸 Google DeepMind	45.7	-	-	-	21.4	-	-	N/A	0K
118	R1🇨🇳 DeepSeekOpen	45.6	15.8	1.3	-	62.3	-	17.1	$0.70	64K
119	Claude Sonnet 4🇺🇸 Anthropic	45.6	40.0	5.9	-	75.3	3.1	34.6	$3.00	200K
120	Grok 3🇺🇸 xAI	45.5	5.5	0.0	-	67.7	-	23.3	N/A	0K
121	Claude Sonnet 4.6🇺🇸 Anthropic	45.4	86.5	60.4	-	86.6	-	-	$3.00	1.0M
122	Qwen3 8B🇨🇳 Alibaba QwenOpen	45.3	-	-	-	42.3	-	-	$0.12	131K
123	o1🇺🇸 OpenAI	45.2	30.7	-	-	71.9	3.3	28.1	$15.00	200K
124	Nemotron 3 Ultra🇺🇸 NVIDIAOpen	45.2	-	-	-	83.8	-	-	$0.60	262K
125	Gemini 3.1 Flash Lite🇺🇸 Google DeepMind	45.0	-	-	-	78.9	4.0	-	$0.25	1.0M
126	DeepSeek R1 Distill Qwen 32B🇨🇳 DeepSeekOpen	44.4	-	-	-	52.2	-	-	N/A	0K
127	Falcon-180B TIIOpen	44.4	-	-	16.1	-	-	-	N/A	0K
128	Qwen2.5 Coder 7B Instruct🇨🇳 AlibabaOpen	44.4	-	-	-	-	-	-	N/A	0K
129	Qwen2.5 Coder 7B Instruct🇨🇳 Alibaba QwenOpen	44.4	-	-	-	-	-	-	$0.03	33K
130	Qwen3.6 Flash🇨🇳 Alibaba QwenOpen	44.0	-	-	-	81.0	-	22.2	$0.19	1.0M
131	GPT-4o-mini (2024-07-18)🇺🇸 OpenAI	43.2	-	0.1	-	17.0	-	-	$0.15	128K
132	GPT-5 Pro🇺🇸 OpenAI	42.7	70.2	18.3	-	-	28.2	53.9	$15.00	400K
133	Qwen3.7 Flash🇨🇳 Alibaba Qwen	42.4	-	-	-	79.6	-	-	$0.03	1.0M
134	Gemma 3 27B (free)🇺🇸 Google DeepMindOpen	42.2	-	-	-	31.8	-	-	Free	131K
135	Qwen3.6 35B A3B🇨🇳 Alibaba QwenOpen	42.2	-	-	-	83.1	-	-	$0.10	262K
136	o1-preview🇺🇸 OpenAI	42.0	18.0	-	-	35.2	-	30.0	N/A	0K
137	Qwen3.7 Plus🇨🇳 Alibaba QwenOpen	41.8	-	-	-	87.3	-	-	$0.32	1.0M
138	Mistral 7B V0.1🇫🇷 Mistral AIOpen	41.6	-	-	41.5	-	-	-	N/A	0K
139	Qwen2.5-Max🇨🇳 Alibaba QwenOpen	41.4	-	-	-	43.2	-	-	N/A	0K
140	Gemini 1.5 Pro (Feb 2024)🇺🇸 Google DeepMind	41.3	-	0.8	78.7	27.8	-	12.5	N/A	0K
141	Mistral Large🇫🇷 Mistral AIOpen	40.8	-	-	-	19.1	-	7.0	$2.00	128K
142	Claude Opus 4.5🇺🇸 Anthropic	40.8	80.0	37.6	-	81.4	21.4	54.4	$5.00	200K
143	Qwen3 14B🇨🇳 Alibaba QwenOpen	40.7	-	-	-	53.8	-	-	$0.12	41K
144	U Baichuan 2-7B Unknown	40.3	-	-	22.1	-	-	-	N/A	0K
145	GPT-4.1🇺🇸 OpenAI	39.5	5.5	0.4	-	55.9	0.6	12.4	$2.00	1.0M
146	Mistral Small 3.1 24B🇫🇷 Mistral AIOpen	39.4	-	-	-	31.2	-	-	$0.35	128K
147	Claude 3.5 Sonnet🇺🇸 Anthropic	39.4	-	-	-	38.7	0.0	13.0	N/A	0K
148	GPT-4 Turbo🇺🇸 OpenAI	39.4	-	-	66.8	7.8	-	10.1	$10.00	128K
149	Gemini 2.5 Flash🇺🇸 Google DeepMind	39.3	32.3	2.5	-	-	7.7	29.4	$0.30	1.0M
150	Mistral Medium 3🇫🇷 Mistral AIOpen	39.3	-	-	-	46.0	0.0	-	$0.40	131K
151	Mistral Large 2407🇫🇷 Mistral AIOpen	39.1	-	-	-	32.0	-	7.0	$2.00	131K
152	GPT-5 Nano🇺🇸 OpenAI	39.1	20.7	2.6	-	61.7	-	-	$0.05	400K
153	Phi 4🇺🇸 MicrosoftOpen	39.1	-	-	-	41.4	-	-	$0.07	16K
154	Qwen3 30B A3B🇨🇳 Alibaba QwenOpen	39.0	-	-	-	50.9	-	-	$0.12	41K
155	Qwen3.5-9B🇨🇳 Alibaba QwenOpen	39.0	-	-	-	75.0	-	-	$0.08	262K
156	Mistral Large 4🇫🇷 Mistral AI	39.0	-	-	-	87.6	-	-	$1.36	1.0M
157	Qwen2.5 Coder 1.5B Instruct🇨🇳 AlibabaOpen	38.8	-	-	-	-	-	-	N/A	0K
158	Gemini 1.5 Pro (May 2024)🇺🇸 Google DeepMind	38.5	-	0.8	85.6	29.0	0.0	12.5	N/A	0K
159	Qwen2-72B🇨🇳 Alibaba QwenOpen	38.4	-	-	-	21.9	-	-	N/A	0K
160	Kimi K2.6🇨🇳 moonshotaiOpen	38.3	-	-	-	91.4	-	-	$0.95	262K
161	Llama 3.1 405B🇺🇸 MetaOpen	38.0	-	-	77.2	36.0	-	7.6	N/A	0K
162	Gemini 2.0 Flash Thinking (Jan 2025)🇺🇸 Google DeepMind	38.0	-	-	-	44.5	1.9	16.8	N/A	0K
163	Claude Sonnet 4.5🇺🇸 Anthropic	37.9	63.7	13.6	-	79.6	9.4	45.2	$3.00	1.0M
164	GPT-5.4 Mini🇺🇸 OpenAI	37.7	63.7	18.9	-	85.9	-	-	$0.75	400K
165	GPT-4.1 Mini🇺🇸 OpenAI	36.7	3.5	0.1	-	56.7	-	-	$0.40	1.0M
166	Claude 3.5 Haiku🇺🇸 Anthropic	36.7	-	-	-	17.5	-	-	N/A	0K
167	Gemma 3 27B🇺🇸 Google DeepMindOpen	36.6	-	-	-	31.8	-	-	$0.08	131K
168	Llama 3.1 70B Instruct🇺🇸 MetaOpen	36.4	-	-	-	26.7	-	-	$0.40	131K
169	Claude Opus 4.1🇺🇸 Anthropic	36.3	-	-	-	69.7	7.1	52.0	$15.00	200K
170	Llama 3.3 70B Instruct🇺🇸 MetaOpen	36.2	-	-	-	31.2	-	3.9	$0.10	131K
171	Llama 3.2 90B🇺🇸 MetaOpen	36.2	-	-	-	22.3	-	-	N/A	0K
172	Gemini 3.5 Flash Lite🇺🇸 Google DeepMind	36.1	53.5	10.3	-	81.0	-	-	$0.30	1.0M
173	GPT-4.5🇺🇸 OpenAI	36.1	10.3	0.8	-	60.7	0.7	21.4	N/A	0K
174	Gemma 2 27B🇺🇸 Google DeepMindOpen	36.0	-	-	-	16.0	-	-	$0.65	8K
175	Gemma 2 9B🇺🇸 Google DeepMindOpen	36.0	-	-	-	3.3	-	-	$0.03	8K
176	Qwen2.5 32B Instruct🇨🇳 AlibabaOpen	35.8	-	-	-	28.1	-	-	N/A	0K
177	GPT-4o (2024-08-06)🇺🇸 OpenAI	35.6	-	-	-	32.3	-	1.4	$2.50	128K
178	Llama 2-13B🇺🇸 MetaOpen	35.3	-	-	44.3	1.8	-	-	N/A	0K
179	o1-mini🇺🇸 OpenAI	35.2	14.0	0.8	-	51.9	-	1.7	N/A	0K
180	LLaMA-13B🇺🇸 MetaOpen	34.9	-	-	17.2	-	-	-	N/A	0K
181	Claude 2🇺🇸 Anthropic	34.4	-	-	-	13.4	-	-	N/A	0K
182	Grok-2 (Dec 2024)🇺🇸 xAI	34.4	-	-	-	40.0	-	7.2	N/A	0K
183	U XGen-7B Unknown	33.9	-	-	-	-	-	-	N/A	0K
184	Qwen3.5-Flash🇨🇳 Alibaba QwenOpen	33.7	-	-	-	79.6	-	-	$0.07	1.0M
185	Claude Haiku 4.5🇺🇸 Anthropic	33.6	47.7	4.0	-	61.6	-	-	$1.00	200K
186	GPT-5.4 Nano🇺🇸 OpenAI	33.6	51.5	5.7	-	74.3	-	-	$0.20	400K
187	Qwen 3.5 Plus (hosted 397B-A17B)🇨🇳 Alibaba QwenOpen	33.6	-	-	-	83.1	-	-	N/A	0K
188	Mistral Nemo🇫🇷 Mistral AIOpen	33.5	-	-	-	6.8	-	-	$0.03	131K
189	GPT-3.5 Turbo (older v0613)🇺🇸 OpenAI	32.8	-	-	48.8	3.0	-	-	$1.00	4K
190	U vicuna-13b-v1.1 Unknown	32.5	-	-	24.1	-	-	-	N/A	0K
191	Llama 3 70B Instruct🇺🇸 MetaOpen	32.4	-	-	-	20.8	-	-	$0.51	8K
192	o3 Mini🇺🇸 OpenAI	32.4	34.5	3.0	-	69.4	-	7.4	$1.10	200K
193	GPT-4o (2024-11-20)🇺🇸 OpenAI	32.3	4.5	0.0	-	30.5	0.0	1.4	$2.50	128K
194	Llama 3-70B🇺🇸 MetaOpen	32.1	-	-	-	21.6	-	-	N/A	0K
195	open_llama_7b🇺🇸 MetaOpen	32.0	-	-	-	-	-	-	N/A	0K
196	U MPT-30B Unknown	31.7	-	-	17.3	-	-	-	N/A	0K
197	QwQ 32B🇨🇳 Alibaba QwenOpen	31.1	-	-	-	56.0	-	-	$0.15	131K
198	Llama 3 8B Instruct🇺🇸 MetaOpen	30.8	-	-	-	1.4	-	-	$0.14	8K
199	Phi 2🇺🇸 MicrosoftOpen	30.2	-	-	45.9	-	-	-	N/A	0K
200	GPT-4.1 Nano🇺🇸 OpenAI	29.3	0.1	0.1	-	33.2	-	-	$0.10	1.0M
201	GPT-4o-mini🇺🇸 OpenAI	29.3	-	0.0	-	17.7	-	0.0	$0.15	128K
202	U Dolly 2.0-12b Unknown	29.2	-	-	-	-	-	-	N/A	0K
203	U Yi 6B UnknownOpen	29.2	-	-	29.6	0.0	-	-	N/A	0K
204	Gemma 2B🇺🇸 Google DeepMindOpen	29.1	-	-	13.6	-	-	-	N/A	0K
205	Llama 3.3 70B Instruct (free)🇺🇸 MetaOpen	29.1	-	-	-	29.9	-	3.9	Free	131K
206	Qwen-1_8B🇨🇳 Alibaba QwenOpen	28.7	-	-	4.3	-	-	-	N/A	0K
207	Claude 3 Opus🇺🇸 Anthropic	28.1	-	-	-	30.8	-	8.2	N/A	0K
208	Llama 4 Maverick🇺🇸 MetaOpen	27.9	4.4	0.1	-	56.0	0.9	13.2	$0.19	524K
209	Claude 3 Sonnet🇺🇸 Anthropic	27.6	-	-	-	21.7	-	-	N/A	0K
210	Claude 3 Haiku🇺🇸 Anthropic	25.8	-	-	-	15.7	-	-	$0.25	200K
211	Command R (08-2024)🇨🇦 Cohere	25.8	-	-	-	-	-	0.9	$0.15	128K
212	DeepSeek Coder 33B🇨🇳 DeepSeekOpen	25.4	-	-	-	-	-	-	N/A	0K
213	Qwen2.5 7B Instruct🇨🇳 Alibaba QwenOpen	24.6	-	-	-	14.6	-	-	$0.10	33K
214	U StarCoder 2 15B UnknownOpen	24.3	-	-	-	-	-	-	N/A	0K
215	Llama 3.1 8B Instruct🇺🇸 MetaOpen	24.3	-	-	-	2.7	-	-	$0.05	131K
216	Mixtral 8x22B Instruct🇫🇷 Mistral AIOpen	23.9	-	-	-	12.6	-	-	$2.00	66K
217	Mistral Small 3.2 24B🇫🇷 Mistral AIOpen	23.9	-	-	-	32.1	-	-	$0.09	256K
218	U Baichuan1-7B Unknown	23.7	-	-	10.0	-	-	-	N/A	0K
219	Cerebras-GPT-13B🇺🇸 OpenAI	23.4	-	-	-	-	-	-	N/A	0K
220	CodeQwen1.5-7B🇨🇳 Alibaba QwenOpen	23.1	-	-	-	-	-	-	N/A	0K
221	Qwen2.5 Coder 0.5B Instruct🇨🇳 AlibabaOpen	20.8	-	-	-	-	-	-	N/A	0K
222	Claude 2.1🇺🇸 Anthropic	20.6	-	-	-	11.1	-	-	N/A	0K
223	Mistral Small 3🇫🇷 Mistral AIOpen	20.3	-	-	-	29.7	-	-	$0.05	33K
224	U INTELLECT-1 Unknown	20.2	-	-	13.1	-	-	-	N/A	0K
225	Llama 4 Scout🇺🇸 MetaOpen	19.5	0.5	0.1	-	35.8	-	-	$0.10	1.3M
226	Gemini 1.0 Pro🇺🇸 Google DeepMind	18.9	-	-	-	12.4	-	-	N/A	0K
227	U RedPajama-INCITE-7B-Base Unknown	18.0	-	-	-	-	-	-	N/A	0K
228	DeepSeek Coder 6.7B🇨🇳 DeepSeekOpen	16.7	-	-	-	-	-	-	N/A	0K
229	U Magistral Small 1.1 Unknown	16.5	5.0	0.0	-	31.2	-	-	N/A	0K
230	Phi-1.5🇺🇸 MicrosoftOpen	16.3	-	-	-	-	-	-	N/A	0K
231	U stablelm-tuned-alpha-7b Unknown	13.6	-	-	-	-	-	-	N/A	0K
232	Gemma 3 12B🇺🇸 Google DeepMindOpen	11.3	-	-	-	20.1	-	-	$0.05	131K
233	Llama 3.2 1B Instruct🇺🇸 MetaOpen	9.4	-	-	-	0.0	-	-	$0.03	60K
234	Gemma 3 4B🇺🇸 Google DeepMindOpen	5.8	-	-	-	0.0	-	-	$0.04	131K
235	DeepSeek Coder 1.3B🇨🇳 DeepSeekOpen	3.2	-	-	-	-	-	-	N/A	0K

90+ Gold 80-89 70-79 60-69 <60Scores in % unless noted. Avg = unweighted mean across tested benchmarks.

About this category

Models ranked by reasoning performance across GPQA Diamond, ARC-AGI, BBH, and other logic and reasoning benchmarks. These tests measure abstract thinking, pattern recognition, and multi-step inference.

Related categories

Best AI Models for Math

AI models ranked by math benchmarks. Compare MATH-500, GSM8K, and competition-level math scores across all providers.

Best AI Models for Knowledge

AI models ranked by knowledge benchmarks. Compare MMLU-Pro, GPQA Diamond, SimpleQA, and other knowledge tests.

Flagship AI Models

The best AI model from each provider, ranked by benchmark score. Compare the flagships from OpenAI, Anthropic, Google, Meta, and more.

Frequently asked questions

Which AI model has the best reasoning?

Reasoning rankings shift as new models launch. The live leaderboard above shows current standings based on GPQA Diamond, ARC-AGI, and other reasoning benchmarks.

What is GPQA Diamond?

GPQA Diamond is a graduate-level question answering benchmark designed to test deep reasoning. Questions are written by domain experts and verified to be answerable only with genuine understanding.

How does ARC-AGI measure reasoning?

ARC-AGI tests abstract reasoning through visual pattern puzzles that require novel inference, not memorization. It is considered one of the hardest AI benchmarks.

Back to all models