AI model leaderboard

Every tracked model ranked across the headline benchmarks. The Intelligence Index averages each model's normalized scores; click any benchmark column header to sort by it.

Best overall

GPT 5.2 Thinking

90.8 Intelligence Index

Best at knowledge

GPT 5.4 Pro

94.4 GPQA Diamond

Best at math

GPT 5.2 Thinking

100.0 AIME 2025

Best at coding

Claude Opus 4.7

87.6 SWE-bench Verified

Best at multimodal

GPT 5.1

84.2 MMMU

Models × benchmarks

Cells are best primary scores. Color intensity reflects normalized score. Click a column header to sort.

#	Model	MMLU-Pro	GPQA Diamond	Humanity's Last Exam	AIME 2025	SWE-bench Verified	LiveCodeBench	MMMU	AA-LCR	Intelligence Index
1	GPT 5.4 Pro	—	94.4%	—	—	—	—	—	—	—
2	Gemini 3.1 Pro	—	94.3%	44.4%	—	80.6%	—	—	—	73.1 3/8
3	Claude Opus 4.7	—	94.2%	46.9%	—	87.6%	—	—	—	76.2 3/8
4	Gemini 3 Deep Think	—	93.8%	41.0%	—	—	—	—	—	—
5	GPT 5.5	—	93.6%	41.4%	—	—	—	—	—	—
6	GPT 5.2 Pro	—	93.2%	—	—	—	—	—	—	—
7	GPT 5.4	—	92.8%	—	—	57.7%	—	—	—	—
8	GPT 5.3 Codex	—	92.6%	—	—	56.8%	—	—	—	—
9	GPT 5.2 Thinking	—	92.4%	—	100.0%	80.0%	—	—	—	90.8 3/8
10	Gemini 3 Pro	—	91.9%	37.5%	95.0%	76.2%	—	—	—	75.2 4/8
11	Claude Opus 4.6	—	91.3%	—	—	80.8%	—	—	—	—
12	GLM 5.2	—	91.2%	40.5%	—	—	—	—	—	—
13	Kimi K2.6	—	90.5%	54.0%	—	80.2%	89.6%	—	—	78.6 4/8
14	Gemini 3 Flash	—	90.4%	—	—	78.0%	—	—	—	—
15	Gemini 3 Flash (Thinking)	—	90.4%	33.7%	95.2%	78.0%	—	—	—	74.3 4/8
16	Claude Sonnet 4.6	—	89.9%	33.2%	—	79.6%	—	—	—	67.6 3/8
17	Kimi K2.7 Code	—	89.6%	32.8%	—	—	—	—	66.3%	62.9 3/8
18	Muse Spark	—	89.5%	42.8%	—	77.4%	—	—	—	69.9 3/8
19	Grok 4 Heavy	—	88.4%	44.4%	100.0%	—	79.4%	—	—	78.1 4/8
20	GPT 5.1	—	88.1%	—	94.6%	74.9%	—	84.2%	—	85.5 4/8
21	GPT 5.1 Thinking	—	88.1%	—	94.6%	—	—	—	—	—
22	GPT 5.4 Mini	—	88.0%	—	—	—	—	—	—	—
23	Qwen 3.6 27B	86.2%	87.8%	24.0%	—	77.2%	83.9%	82.9%	—	73.7 6/8
24	Grok 4	—	87.5%	25.4%	91.7%	—	79.0%	—	—	70.9 4/8
25	Claude Opus 4.5	—	87.0%	—	—	80.9%	—	80.7%	—	82.9 3/8
26	Qwen 3.5 122B A10B	—	86.6%	—	—	72.0%	—	76.9%	—	78.5 3/8
27	Gemini 2.5 Pro (Thinking)	—	86.4%	21.6%	88.0%	59.6%	—	—	—	63.9 4/8
28	GLM-5.1	—	86.2%	31.0%	—	—	—	—	—	—
29	GLM 5	—	86.0%	—	—	77.8%	—	—	—	—
30	GPT 5 (Thinking)	—	85.7%	24.8%	94.6%	74.9%	—	84.2%	—	72.8 5/8
31	Qwen 3.5 27B	86.1%	85.5%	—	—	72.4%	—	—	—	81.3 3/8
32	Grok 3 Think	—	84.6%	—	93.3%	—	79.4%	—	—	85.8 3/8
33	Gemma 4	85.2%	84.3%	—	—	—	80.0%	—	—	83.2 3/8
34	Qwen 3.5 35B A3B	—	84.2%	—	—	69.2%	—	—	—	—
35	Gemini 2.5 Pro	—	84.0%	18.8%	86.7%	63.8%	70.4%	—	—	64.7 5/8
36	Claude Sonnet 4.5	—	83.4%	—	87.0%	77.2%	—	77.8%	—	81.4 4/8
37	o3	—	83.3%	20.3%	88.9%	69.1%	—	82.9%	—	68.9 5/8
38	GPT 5.4 Nano	—	82.8%	—	—	—	—	—	—	—
39	Gemini 2.5 Flash (Thinking)	—	82.8%	11.0%	72.0%	60.4%	—	—	—	56.6 4/8
40	Deepseek 3.2	85.0%	82.4%	40.8%	93.1%	73.1%	83.3%	—	—	76.3 6/8
41	GLM 4.6	—	81.0%	17.2%	93.9%	68.0%	82.8%	—	—	68.6 5/8
42	Opus 4.1 Thinking	—	80.9%	—	—	74.5%	—	—	—	—
43	DeepSeek V3.1 Terminus	85.0%	80.7%	21.7%	88.4%	—	74.9%	—	—	70.1 5/8
44	GPT OSS 120B	90.0%	80.1%	—	—	—	—	—	—	—
45	DeepSeek V3.2 Exp	85.0%	79.9%	—	89.3%	67.8%	74.1%	—	—	79.2 5/8
46	Claude Sonnet 3.7 (Thinking)	—	78.2%	—	—	62.3%	—	75.0%	—	71.8 3/8
47	o1	—	78.0%	8.12%	79.2%	48.9%	—	77.6%	—	58.4 5/8
48	GPT 5	—	77.8%	6.30%	61.9%	52.8%	—	74.4%	—	54.6 5/8
49	Trinity Large Thinking	83.4%	76.3%	—	96.3%	63.2%	—	—	—	79.8 4/8
50	Llama 3.1 Nemotron Ultra	—	76.0%	—	—	—	—	—	—	—
51	Claude Sonnet 4	—	75.4%	—	70.5%	72.7%	—	74.4%	—	73.3 4/8
52	Grok 3	79.9%	75.4%	—	—	—	57.0%	73.2%	—	71.4 4/8
53	Kimi K2 Instruct	—	75.1%	—	49.5%	65.8%	53.7%	—	—	61.0 4/8
54	Nemotron 3 Nano	78.3%	75.0%	—	89.1%	—	68.3%	—	—	77.7 4/8
55	Nemotron 3	78.3%	75.0%	—	89.1%	38.8%	68.3%	—	—	69.9 5/8
56	Llama 4 Behemoth	82.2%	73.7%	—	—	—	49.4%	76.1%	—	70.4 4/8
57	Claude Haiku 4.5	—	73.0%	—	80.7%	73.3%	—	73.2%	—	75.1 4/8
58	Gemma 3	78.0%	72.6%	—	—	—	—	—	—	—
59	DeepSeek-R1	84.0%	71.5%	—	70.0%	49.2%	—	—	—	68.7 4/8
60	R1 1776	—	71.5%	—	70.0%	—	—	—	—	—
61	Magistral Medium	—	70.8%	—	64.9%	—	50.3%	—	—	62.0 3/8
62	Llama 4 Maverick	80.5%	69.8%	—	—	—	43.4%	73.4%	—	66.8 4/8
63	Phi 4 reasoning plus	76.0%	69.3%	—	78.0%	—	—	—	—	74.4 3/8
64	GPT 4.1	—	66.3%	—	—	55.0%	—	75.0%	—	65.4 3/8
65	Grok 3 mini	78.9%	66.2%	—	—	—	41.5%	69.4%	—	64.0 4/8
66	Qwen3-30B-A3B	—	65.8%	—	—	—	—	—	—	—
67	Qwen3 30B A3B	—	65.8%	—	70.9%	—	62.6%	—	—	66.4 3/8
68	Claude Haiku 3.5	41.6%	65.0%	—	—	40.6%	—	—	—	49.1 3/8
69	Seed 1.5	80.1%	65.0%	—	—	—	—	73.9%	—	73.0 3/8
70	Gemini 2.5 Flash-Lite	—	64.6%	5.10%	49.8%	31.6%	33.7%	72.9%	—	43.0 6/8
71	Claude Sonnet 3.7	—	62.3%	—	—	62.3%	—	71.8%	—	65.5 3/8
72	Nemotron 3 Super	75.7%	60.0%	—	—	—	—	—	—	—
73	DeepSeek V3	75.9%	59.1%	—	—	42.0%	—	—	—	59.0 3/8
74	Llama 4 Scout	74.3%	57.2%	—	—	—	32.8%	69.4%	—	58.4 4/8
75	GPT-4o	—	53.6%	—	—	—	—	69.1%	—	—
76	Command A	69.6%	50.8%	—	—	—	—	—	—	—
77	Llama 3.3	68.9%	50.5%	—	—	—	—	—	—	—
78	GPT-4 Turbo	—	50.4%	—	—	—	—	—	—	—
79	Claude Opus 3	—	50.4%	—	—	—	—	—	—	—
80	Nova Pro	—	46.9%	—	—	—	—	—	—	—
81	Mistral Large 3	—	43.9%	—	—	—	34.4%	—	—	—
82	Nova Lite	—	42.0%	—	—	—	—	—	—	—
83	Nova Micro	—	40.0%	—	—	—	—	—	—	—
84	Llama 3.2	—	32.8%	—	—	—	—	—	—	—
85	Claude Sonnet 5	—	—	43.2%	—	—	—	—	—	—
86	DeepSeek 3.2 Speciale	—	—	30.6%	96.0%	—	—	—	—	—
87	Deepseek V4 Pro	—	—	—	—	—	93.5%	—	—	—
88	Devstral 2	—	—	—	—	72.2%	—	—	—	—
89	GPT 5.5 Instant	—	—	—	81.2%	—	—	—	—	—
90	Grok Code Fast 1	—	—	—	—	70.8%	—	—	—	—
91	Kimi K2.5	—	—	—	—	76.8%	85.0%	—	—	—
92	MiMo V2.5 Pro	—	—	48.0%	—	78.9%	—	—	—	—
93	MiniMax M2.5	—	—	—	—	80.2%	—	—	—	—
94	Mistral Medium 3.5	—	—	—	—	77.6%	—	—	—	—
95	Mistral Small 3	66.3%	—	—	—	—	—	—	—	—
96	Nova Premier	—	—	—	—	42.4%	—	—	—	—
97	o4 mini	—	—	—	92.7%	68.1%	—	81.6%	—	80.8 3/8
98	Pixtral 12B	—	—	—	—	—	—	52.0%	—	—
99	Pixtral Large	—	—	—	—	—	—	64.0%	—	—
100	Qwen3 235B A22B	—	—	—	81.5%	—	70.7%	—	—	—

Capability scatter

Each dot is a model. Position shows two-axis capability; size reflects how many headline benchmarks the model has been scored on.

X axis Y axis

Go to section

Search

AI model leaderboard

Models × benchmarks

Capability scatter

Help

People also viewed

Create AI Tools

Mini Tool

Vibe code an AI Tool

Choose listing type: