Best AI Models for Math

Q: Which AI model is best at math?

Math rankings are updated live. Check the leaderboard above for the current leader on MATH-500, GSM8K, and competition-level math benchmarks.

Q: What is MATH-500?

MATH-500 is a curated subset of 500 competition-level math problems spanning multiple difficulty levels and topics including algebra, number theory, and geometry.

Q: Can AI solve competition math problems?

Top models now score above 95% on MATH-500 and are approaching human-competitive levels on AIME and Olympiad-style problems.

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

211

Models

Providers

101

Open Source

$0.60

Median $/1M in

Top 3

Full Rankings

#	Model	Avg	frontierma	GSM8K	MATH level 5	otis mock	$/1M in	Context
1	GPT-6.1 Sol🇺🇸 OpenAI	77.3	-	-	-	100.0	$2.00	1.1M
2	Gemini 4 Argon🇺🇸 Google DeepMind	76.5	-	-	-	100.0	$2.00	1.0M
3	GPT-6 Astra🇺🇸 OpenAI	74.7	-	-	-	100.0	$10.00	1.1M
4	Claude Opus 5.5🇺🇸 Anthropic	74.0	-	-	-	100.0	$4.00	1.0M
5	Claude Opus 5🇺🇸 Anthropic	68.4	-	-	-	98.9	$5.00	1.0M
6	Claude Fable 5.1🇺🇸 Anthropic	68.2	-	-	-	100.0	$10.00	1.0M
7	Claude Sonnet 5.5🇺🇸 Anthropic	67.8	-	-	-	100.0	$2.00	1.0M
8	Claude Fable 5🇺🇸 Anthropic	67.6	-	-	-	100.0	$10.00	1.0M
9	GPT-6 Sol🇺🇸 OpenAI	67.5	-	-	-	100.0	$2.00	1.1M
10	GPT-5.6 Terra🇺🇸 OpenAI	66.9	-	-	-	99.7	$2.00	1.1M
11	GPT-5.6 Sol🇺🇸 OpenAI	65.8	-	-	-	100.0	$2.00	1.1M
12	GPT-5.4 Pro🇺🇸 OpenAI	64.8	50.0	-	-	-	$30.00	1.1M
13	Claude Instant🇺🇸 Anthropic	64.3	-	86.7	-	-	N/A	0K
14	Muse Spark Open🇺🇸 Meta	63.6	-	-	-	98.0	$1.25	1.0M
15	Qwen3.7 Max🇨🇳 Alibaba QwenOpen	62.0	-	-	-	95.5	$1.48	1.0M
16	Qwen-14B🇨🇳 Alibaba QwenOpen	60.7	-	61.3	-	-	N/A	0K
17	DeepSeek V4 Pro 0813🇨🇳 DeepSeek	60.4	-	-	-	98.6	$1.32	1.0M
18	Qwen3.5 397B A17B🇨🇳 Alibaba QwenOpen	60.3	-	-	-	88.9	$0.50	262K
19	Gemini 3.7 Flash🇺🇸 Google DeepMind	59.1	-	-	-	97.2	$0.75	1.0M
20	U internlm-20b Unknown	59.0	-	62.9	-	-	N/A	0K
21	phi-3-medium 14B🇺🇸 MicrosoftOpen	58.6	-	-	17.6	-	N/A	0K
22	GPT-5.2 Pro🇺🇸 OpenAI	58.1	-	-	-	-	$21.00	400K
23	Gemini 3.8 Flash🇺🇸 Google DeepMind	58.0	-	-	-	98.9	$0.82	1.0M
24	Falcon 2 11B TIIOpen	58.0	-	53.8	-	-	N/A	0K
25	R1 0528🇨🇳 DeepSeekOpen	57.9	-	-	96.6	66.4	$0.50	164K
26	Mixtral 8x7B Instruct🇫🇷 Mistral AIOpen	57.8	-	74.4	9.9	-	$0.54	33K
27	Kimi K3🇨🇳 moonshotai	57.8	-	-	-	97.2	$0.24	1.0M
28	Claude Sonnet 5🇺🇸 Anthropic	57.7	-	-	-	94.7	$2.00	1.0M
29	Grok 4.6🇺🇸 xAI	57.5	-	-	-	99.2	$2.00	500K
30	Qwen3.6 27B🇨🇳 Alibaba QwenOpen	57.3	-	-	-	91.1	$0.25	262K
31	GLM 5.3🇨🇳 z-ai	56.7	-	-	-	91.1	$0.08	1.0M
32	Claude Haiku 5.5🇺🇸 Anthropic	56.5	-	-	-	98.9	$0.10	1.0M
33	Claude Opus 4.8🇺🇸 Anthropic	56.4	47.2	-	-	98.3	$5.00	1.0M
34	GLM 5.2🇨🇳 z-aiOpen	56.3	-	-	-	86.4	$0.03	1.0M
35	Grok 4.3🇺🇸 xAI	56.3	-	-	-	93.3	$1.25	1.0M
36	Gemini 3 Pro🇺🇸 Google DeepMind	56.2	66.0	-	-	91.4	N/A	0K
37	Kimi K2.7 Code🇨🇳 moonshotaiOpen	56.2	-	-	-	95.5	$0.67	262K
38	DeepSeek V3🇨🇳 DeepSeekOpen	56.2	3.0	-	64.8	15.8	$0.26	164K
39	Muse Spark🇺🇸 Meta	56.1	68.4	-	-	88.9	N/A	0K
40	DeepSeek V4 Flash 0731🇨🇳 DeepSeek	55.7	-	-	-	94.4	$0.44	1.0M
41	GPT-5.6 Luna🇺🇸 OpenAI	55.3	-	-	-	98.3	$0.20	1.1M
42	Qwen3.8 Max (0902)🇨🇳 Alibaba Qwen	55.3	-	-	-	99.4	$2.00	1.0M
43	GPT-4 (older v0314)🇺🇸 OpenAI	55.0	-	92.0	-	0.5	$30.00	8K
44	Gemini 3.5 Flash🇺🇸 Google DeepMind	54.9	39.0	-	-	95.5	$1.50	1.0M
45	GLM 5🇨🇳 z-aiOpen	54.7	16.4	-	-	80.0	$1.00	205K
46	GLM 5.1🇨🇳 z-aiOpen	54.6	33.5	-	-	93.3	$1.40	205K
47	Grok 4.5🇺🇸 xAI	54.5	-	-	-	97.8	$2.00	500K
48	Mixtral 8x7B🇫🇷 Mistral AIOpen	54.3	-	74.4	9.9	-	N/A	0K
49	Gemini 2.0 Pro🇺🇸 Google DeepMind	54.3	-	-	83.5	-	N/A	0K
50	DeepSeek V4 Pro🇨🇳 DeepSeekOpen	54.1	-	-	-	96.7	$0.96	1.0M
51	DeepSeek V4.1 Flash🇨🇳 DeepSeekOpen	54.1	-	-	-	98.3	$0.30	1.0M
52	Gemini 3.6 Flash🇺🇸 Google DeepMind	54.1	-	-	-	94.2	$0.75	1.0M
53	Grok 4🇺🇸 xAI	54.0	19.7	-	-	84.0	N/A	0K
54	Qwen3 235B A22B🇨🇳 Alibaba QwenOpen	53.7	-	-	68.9	-	$0.46	131K
55	Grok-3 mini🇺🇸 xAI	53.7	10.3	-	90.9	77.8	N/A	0K
56	Qwen3.6 Plus🇨🇳 Alibaba QwenOpen	53.6	26.2	-	-	93.3	$0.33	1.0M
57	U Nemotron-4 15B Unknown	53.4	-	46.0	-	-	N/A	0K
58	gpt-oss-20b🇺🇸 OpenAIOpen	53.2	-	-	-	65.2	$0.02	131K
59	GPT-5🇺🇸 OpenAI	53.2	32.4	-	98.1	91.4	$1.25	400K
60	Qwen2.5 Coder 32B Instruct🇨🇳 Alibaba QwenOpen	53.1	-	91.1	-	-	$0.66	33K
61	Qwen3 235B A22B Thinking 2507🇨🇳 Alibaba QwenOpen	53.1	14.9	-	-	86.7	$0.45	128K
62	Gemma 4 31B🇺🇸 Google DeepMindOpen	53.0	-	-	-	73.3	$0.09	262K
63	Qwen2.5-Coder-3B🇨🇳 Alibaba QwenOpen	52.2	-	75.7	-	-	N/A	0K
64	Kimi K2 Thinking🇨🇳 moonshotaiOpen	52.2	21.4	-	-	83.0	$0.60	262K
65	GPT-5.4🇺🇸 OpenAI	52.1	47.6	-	-	97.8	$2.50	1.1M
66	DeepSeek R1 Distill Qwen 14B🇨🇳 DeepSeekOpen	52.0	-	-	87.1	50.5	N/A	0K
67	Qwen3 32B🇨🇳 Alibaba QwenOpen	51.7	-	-	-	66.9	$0.08	131K
68	Qwen3.5-35B-A3B🇨🇳 Alibaba QwenOpen	51.6	-	-	-	70.0	$0.14	262K
69	GPT-5 Mini🇺🇸 OpenAI	51.5	27.2	-	97.8	86.7	$0.25	400K
70	o3🇺🇸 OpenAI	51.3	18.7	-	97.8	84.4	$2.00	200K
71	Claude Opus 4.7🇺🇸 Anthropic	51.2	43.8	-	-	97.8	$5.00	1.0M
72	GPT-4o (2024-05-13)🇺🇸 OpenAI	51.1	-	-	51.0	6.2	$5.00	128K
73	GPT-6 Luna🇺🇸 OpenAI	51.1	-	-	-	98.9	$0.10	1.1M
74	Qwen3.6 Max Preview🇨🇳 Alibaba QwenOpen	51.0	40.5	-	-	91.1	$1.03	262K
75	Gemini 2.5 Pro🇺🇸 Google DeepMind	50.9	14.1	-	95.6	84.7	$1.25	1.0M
76	DeepSeek-Coder-V2-Lite-Base🇨🇳 DeepSeekOpen	50.8	-	67.1	-	-	N/A	0K
77	GLM 4.6🇨🇳 z-aiOpen	50.8	3.8	-	-	-	$0.43	205K
78	Grok 4.7🇺🇸 xAI	50.7	-	-	-	98.0	$2.00	500K
79	Qwen2.5 Coder 14B Instruct🇨🇳 AlibabaOpen	50.0	-	88.7	-	-	N/A	0K
80	MiniMax M3🇨🇳 minimaxOpen	50.0	-	-	-	71.1	$0.30	1.0M
81	Gemini 3 Flash Preview🇺🇸 Google DeepMind	49.8	35.6	-	-	92.8	$0.50	1.0M
82	Grok 4.20🇺🇸 xAI	49.5	-	-	-	92.2	$1.25	2.0M
83	Kimi K2.5🇨🇳 moonshotaiOpen	49.5	27.9	-	-	92.2	$0.50	262K
84	gpt-oss-120b🇺🇸 OpenAIOpen	49.3	-	-	-	88.9	$0.04	131K
85	Qwen2.5 72B Instruct🇨🇳 Alibaba QwenOpen	49.3	-	-	63.2	8.0	$0.36	33K
86	o4 Mini🇺🇸 OpenAI	48.6	24.8	-	97.8	81.7	$1.10	200K
87	DeepSeek V3.2🇨🇳 DeepSeekOpen	48.3	38.8	-	-	87.8	$0.28	164K
88	Claude Opus 4.6🇺🇸 Anthropic	48.3	40.7	-	-	94.4	$5.00	1.0M
89	Gemini 3.1 Pro Preview🇺🇸 Google DeepMind	48.2	36.9	-	-	95.6	$2.00	1.0M
90	Claude 3.7 Sonnet🇺🇸 Anthropic	48.2	4.1	-	91.2	57.7	N/A	0K
91	GLM 5.3 Flash🇨🇳 z-ai	48.1	-	-	-	93.9	$0.02	1.0M
92	Gemini 2.0 Flash🇺🇸 Google DeepMind	48.0	1.7	-	82.2	31.0	$0.10	1.0M
93	Gemini 2.0 Flash (Dec 2024)🇺🇸 Google DeepMind	47.8	3.0	-	82.2	31.0	N/A	0K
94	U Stable Beluga 2 Unknown	47.8	-	69.6	-	-	N/A	0K
95	GPT-5.1🇺🇸 OpenAI	47.5	31.0	-	-	88.6	$1.25	400K
96	GLM 4.7🇨🇳 z-aiOpen	46.7	4.3	-	-	83.3	$0.60	205K
97	Qwen3 Max🇨🇳 Alibaba QwenOpen	46.5	-	-	97.1	73.3	$0.78	262K
98	Gemma 4 26B A4B 🇺🇸 Google DeepMindOpen	46.4	-	-	-	82.2	$0.08	262K
99	GPT-5.2🇺🇸 OpenAI	46.1	40.7	-	-	96.1	$1.75	400K
100	Claude Opus 4🇺🇸 Anthropic	46.1	7.9	-	85.0	64.4	$15.00	200K
101	Mistral Large 2411🇫🇷 Mistral AIOpen	45.8	0.3	-	50.3	7.7	$2.00	131K
102	Gemini 1.5 Flash (May 2024)🇺🇸 Google DeepMind	45.7	0.0	82.4	25.1	3.8	N/A	0K
103	R1🇨🇳 DeepSeekOpen	45.6	-	-	93.0	53.3	$0.70	64K
104	Claude Sonnet 4🇺🇸 Anthropic	45.6	7.3	-	84.4	71.1	$3.00	200K
105	Grok 3🇺🇸 xAI	45.5	3.8	-	88.8	55.5	N/A	0K
106	Claude Sonnet 4.6🇺🇸 Anthropic	45.4	32.4	-	-	85.8	$3.00	1.0M
107	Qwen3 8B🇨🇳 Alibaba QwenOpen	45.3	-	-	-	56.1	$0.12	131K
108	o1🇺🇸 OpenAI	45.2	9.3	-	94.7	73.3	$15.00	200K
109	Nemotron 3 Ultra🇺🇸 NVIDIAOpen	45.2	-	-	-	86.7	$0.60	262K
110	Gemini 3.1 Flash Lite🇺🇸 Google DeepMind	45.0	-	-	-	80.0	$0.25	1.0M
111	DeepSeek R1 Distill Qwen 32B🇨🇳 DeepSeekOpen	44.4	-	-	-	55.5	N/A	0K
112	Falcon-180B TIIOpen	44.4	-	54.4	-	-	N/A	0K
113	Qwen2.5 Coder 7B Instruct🇨🇳 AlibabaOpen	44.4	-	86.7	-	-	N/A	0K
114	Qwen2.5 Coder 7B Instruct🇨🇳 Alibaba QwenOpen	44.4	-	86.7	-	-	$0.03	33K
115	Qwen3.6 Flash🇨🇳 Alibaba QwenOpen	44.0	10.3	-	-	84.4	$0.19	1.0M
116	GPT-4o-mini (2024-07-18)🇺🇸 OpenAI	43.2	-	91.3	52.6	6.8	$0.15	128K
117	GPT-5 Pro🇺🇸 OpenAI	42.7	-	-	-	-	$15.00	400K
118	Qwen3.7 Flash🇨🇳 Alibaba Qwen	42.4	-	-	-	86.7	$0.03	1.0M
119	Gemma 3 27B (free)🇺🇸 Google DeepMindOpen	42.2	-	-	74.0	19.6	Free	131K
120	Qwen3.6 35B A3B🇨🇳 Alibaba QwenOpen	42.2	-	-	-	86.7	$0.10	262K
121	o1-preview🇺🇸 OpenAI	42.0	-	-	81.7	31.0	N/A	0K
122	Qwen3.7 Plus🇨🇳 Alibaba QwenOpen	41.8	-	-	-	93.3	$0.32	1.0M
123	Mistral 7B V0.1🇫🇷 Mistral AIOpen	41.6	-	54.4	-	-	N/A	0K
124	Qwen2.5-Max🇨🇳 Alibaba QwenOpen	41.4	1.8	-	67.2	16.0	N/A	0K
125	Gemini 1.5 Pro (Feb 2024)🇺🇸 Google DeepMind	41.3	-	-	40.8	6.7	N/A	0K
126	Mistral Large🇫🇷 Mistral AIOpen	40.8	0.6	-	24.5	1.9	$2.00	128K
127	Claude Opus 4.5🇺🇸 Anthropic	40.8	20.7	-	-	86.1	$5.00	200K
128	Qwen3 14B🇨🇳 Alibaba QwenOpen	40.7	-	-	-	66.4	$0.12	41K
129	U Baichuan 2-7B Unknown	40.3	-	24.6	-	-	N/A	0K
130	GPT-4.1🇺🇸 OpenAI	39.5	5.5	-	83.0	38.3	$2.00	1.0M
131	Mistral Small 3.1 24B🇫🇷 Mistral AIOpen	39.4	-	-	46.8	5.7	$0.35	128K
132	Claude 3.5 Sonnet🇺🇸 Anthropic	39.4	1.8	-	51.7	6.4	N/A	0K
133	GPT-4 Turbo🇺🇸 OpenAI	39.4	-	90.0	23.0	1.0	$10.00	128K
134	Gemini 2.5 Flash🇺🇸 Google DeepMind	39.3	8.5	-	-	73.0	$0.30	1.0M
135	Mistral Medium 3🇫🇷 Mistral AIOpen	39.3	0.6	-	81.6	32.1	$0.40	131K
136	Mistral Large 2407🇫🇷 Mistral AIOpen	39.1	-	-	44.8	8.4	$2.00	131K
137	GPT-5 Nano🇺🇸 OpenAI	39.1	8.3	-	95.2	81.1	$0.05	400K
138	Phi 4🇺🇸 MicrosoftOpen	39.1	-	-	64.9	13.7	$0.07	16K
139	Qwen3 30B A3B🇨🇳 Alibaba QwenOpen	39.0	-	-	-	62.7	$0.12	41K
140	Qwen3.5-9B🇨🇳 Alibaba QwenOpen	39.0	-	-	-	61.6	$0.08	262K
141	Mistral Large 4🇫🇷 Mistral AI	39.0	-	-	-	98.3	$1.36	1.0M
142	Qwen2.5 Coder 1.5B Instruct🇨🇳 AlibabaOpen	38.8	-	65.8	-	-	N/A	0K
143	Gemini 1.5 Pro (May 2024)🇺🇸 Google DeepMind	38.5	-	-	40.8	6.7	N/A	0K
144	Qwen2-72B🇨🇳 Alibaba QwenOpen	38.4	-	-	39.1	-	N/A	0K
145	Kimi K2.6🇨🇳 moonshotaiOpen	38.3	39.0	-	-	96.1	$0.95	262K
146	Llama 3.1 405B🇺🇸 MetaOpen	38.0	-	-	49.8	9.6	N/A	0K
147	Gemini 2.0 Flash Thinking (Jan 2025)🇺🇸 Google DeepMind	38.0	-	-	-	57.7	N/A	0K
148	Claude Sonnet 4.5🇺🇸 Anthropic	37.9	15.2	-	97.7	77.8	$3.00	1.0M
149	GPT-5.4 Mini🇺🇸 OpenAI	37.7	28.3	-	-	88.9	$0.75	400K
150	GPT-4.1 Mini🇺🇸 OpenAI	36.7	4.5	-	87.3	44.7	$0.40	1.0M
151	Claude 3.5 Haiku🇺🇸 Anthropic	36.7	0.6	-	46.4	4.2	N/A	0K
152	Gemma 3 27B🇺🇸 Google DeepMindOpen	36.6	-	-	74.0	22.4	$0.08	131K
153	Llama 3.1 70B Instruct🇺🇸 MetaOpen	36.4	-	-	36.7	3.5	$0.40	131K
154	Claude Opus 4.1🇺🇸 Anthropic	36.3	7.2	-	-	68.9	$15.00	200K
155	Llama 3.3 70B Instruct🇺🇸 MetaOpen	36.2	-	-	41.6	5.0	$0.10	131K
156	Llama 3.2 90B🇺🇸 MetaOpen	36.2	-	-	39.4	2.5	N/A	0K
157	Gemini 3.5 Flash Lite🇺🇸 Google DeepMind	36.1	-	-	-	71.1	$0.30	1.0M
158	GPT-4.5🇺🇸 OpenAI	36.1	-	-	78.6	37.7	N/A	0K
159	Gemma 2 27B🇺🇸 Google DeepMindOpen	36.0	-	84.9	27.9	1.3	$0.65	8K
160	Gemma 2 9B🇺🇸 Google DeepMindOpen	36.0	-	84.9	21.0	0.5	$0.03	8K
161	Qwen2.5 32B Instruct🇨🇳 AlibabaOpen	35.8	-	-	56.1	7.3	N/A	0K
162	GPT-4o (2024-08-06)🇺🇸 OpenAI	35.6	0.3	-	53.3	6.3	$2.50	128K
163	Llama 2-13B🇺🇸 MetaOpen	35.3	-	36.9	3.3	0.0	N/A	0K
164	o1-mini🇺🇸 OpenAI	35.2	3.0	-	89.2	46.9	N/A	0K
165	LLaMA-13B🇺🇸 MetaOpen	34.9	-	20.6	-	-	N/A	0K
166	Claude 2🇺🇸 Anthropic	34.4	-	-	11.7	2.4	N/A	0K
167	Grok-2 (Dec 2024)🇺🇸 xAI	34.4	1.2	-	63.5	11.4	N/A	0K
168	Qwen3.5-Flash🇨🇳 Alibaba QwenOpen	33.7	6.2	-	-	84.4	$0.07	1.0M
169	Claude Haiku 4.5🇺🇸 Anthropic	33.6	10.4	-	96.4	66.6	$1.00	200K
170	GPT-5.4 Nano🇺🇸 OpenAI	33.6	25.9	-	-	87.8	$0.20	400K
171	Qwen 3.5 Plus (hosted 397B-A17B)🇨🇳 Alibaba QwenOpen	33.6	36.9	-	-	86.7	N/A	0K
172	Mistral Nemo🇫🇷 Mistral AIOpen	33.5	-	84.2	10.8	-	$0.03	131K
173	GPT-3.5 Turbo (older v0613)🇺🇸 OpenAI	32.8	-	57.8	11.6	2.1	$1.00	4K
174	U vicuna-13b-v1.1 Unknown	32.5	-	28.1	-	-	N/A	0K
175	Llama 3 70B Instruct🇺🇸 MetaOpen	32.4	-	-	22.6	4.2	$0.51	8K
176	o3 Mini🇺🇸 OpenAI	32.4	12.4	-	96.5	76.9	$1.10	200K
177	GPT-4o (2024-11-20)🇺🇸 OpenAI	32.3	0.3	-	49.8	6.2	$2.50	128K
178	Llama 3-70B🇺🇸 MetaOpen	32.1	-	-	22.6	4.2	N/A	0K
179	U MPT-30B Unknown	31.7	-	34.4	-	-	N/A	0K
180	QwQ 32B🇨🇳 Alibaba QwenOpen	31.1	-	-	-	59.1	$0.15	131K
181	Llama 3 8B Instruct🇺🇸 MetaOpen	30.8	-	-	6.1	0.7	$0.14	8K
182	GPT-4.1 Nano🇺🇸 OpenAI	29.3	1.0	-	70.0	28.8	$0.10	1.0M
183	GPT-4o-mini🇺🇸 OpenAI	29.3	-	91.3	52.6	6.8	$0.15	128K
184	U Yi 6B UnknownOpen	29.2	-	44.9	5.2	-	N/A	0K
185	Gemma 2B🇺🇸 Google DeepMindOpen	29.1	-	17.7	-	-	N/A	0K
186	Llama 3.3 70B Instruct (free)🇺🇸 MetaOpen	29.1	-	-	41.6	5.0	Free	131K
187	Qwen-1_8B🇨🇳 Alibaba QwenOpen	28.7	-	21.2	-	-	N/A	0K
188	Claude 3 Opus🇺🇸 Anthropic	28.1	-	-	37.5	4.6	N/A	0K
189	Llama 4 Maverick🇺🇸 MetaOpen	27.9	1.2	-	73.0	20.5	$0.19	524K
190	Claude 3 Sonnet🇺🇸 Anthropic	27.6	-	-	18.2	2.4	N/A	0K
191	Claude 3 Haiku🇺🇸 Anthropic	25.8	-	-	14.9	1.7	$0.25	200K
192	DeepSeek Coder 33B🇨🇳 DeepSeekOpen	25.4	-	35.4	-	-	N/A	0K
193	Qwen2.5 7B Instruct🇨🇳 Alibaba QwenOpen	24.6	-	-	-	2.4	$0.10	33K
194	U StarCoder 2 15B UnknownOpen	24.3	-	57.7	-	-	N/A	0K
195	Llama 3.1 8B Instruct🇺🇸 MetaOpen	24.3	-	82.4	22.9	1.6	$0.05	131K
196	Mixtral 8x22B Instruct🇫🇷 Mistral AIOpen	23.9	-	-	24.2	-	$2.00	66K
197	Mistral Small 3.2 24B🇫🇷 Mistral AIOpen	23.9	-	-	-	30.2	$0.09	256K
198	U Baichuan1-7B Unknown	23.7	-	9.2	-	-	N/A	0K
199	CodeQwen1.5-7B🇨🇳 Alibaba QwenOpen	23.1	-	37.7	-	-	N/A	0K
200	Qwen2.5 Coder 0.5B Instruct🇨🇳 AlibabaOpen	20.8	-	34.5	-	-	N/A	0K
201	Claude 2.1🇺🇸 Anthropic	20.6	-	-	-	1.9	N/A	0K
202	Mistral Small 3🇫🇷 Mistral AIOpen	20.3	-	-	44.8	6.6	$0.05	33K
203	U INTELLECT-1 Unknown	20.2	-	38.6	-	-	N/A	0K
204	Llama 4 Scout🇺🇸 MetaOpen	19.5	0.0	-	62.3	7.7	$0.10	1.3M
205	Gemini 1.0 Pro🇺🇸 Google DeepMind	18.9	-	-	11.2	1.0	N/A	0K
206	DeepSeek Coder 6.7B🇨🇳 DeepSeekOpen	16.7	-	21.3	-	-	N/A	0K
207	U Magistral Small 1.1 Unknown	16.5	-	-	-	29.9	N/A	0K
208	Gemma 3 12B🇺🇸 Google DeepMindOpen	11.3	-	-	-	16.6	$0.05	131K
209	Llama 3.2 1B Instruct🇺🇸 MetaOpen	9.4	-	-	-	0.5	$0.03	60K
210	Gemma 3 4B🇺🇸 Google DeepMindOpen	5.8	-	-	-	7.4	$0.04	131K
211	DeepSeek Coder 1.3B🇨🇳 DeepSeekOpen	3.2	-	4.4	-	-	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 mathematical ability across MATH-500, GSM8K, FrontierMath, and competition-level problems. Scores reflect arithmetic, algebra, geometry, combinatorics, and proof-based reasoning.

Related categories

Best AI Models for Reasoning

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

Best AI Models for Coding

AI models ranked by coding benchmarks. Compare HumanEval+, SWE-bench Verified, Aider Polyglot, and more across all providers.

Best AI Models for Knowledge

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

Frequently asked questions

Which AI model is best at math?

Math rankings are updated live. Check the leaderboard above for the current leader on MATH-500, GSM8K, and competition-level math benchmarks.

What is MATH-500?

MATH-500 is a curated subset of 500 competition-level math problems spanning multiple difficulty levels and topics including algebra, number theory, and geometry.

Can AI solve competition math problems?

Top models now score above 95% on MATH-500 and are approaching human-competitive levels on AIME and Olympiad-style problems.

Back to all models