AI Model Ranking

Transparent, explainable model scores based on benchmark results, capabilities, price and context.

Overall = Benchmark 50% + Capability 20% + Price Efficiency 20% + Context 10%.

Rank	Model	Score	Data Confidence	Rank Change	Benchmark	Price Efficiency	Capability
1	Claude 3.5 Sonnet	78.4	Data Confidence 95% 2 sources	→	80	100	85.7
2	Gemini 1.5 Pro	76.9	Data Confidence 95% 2 sources	→	70.8	100	100
3	Mistral Large 2	73.6	Data Confidence 50% 2 sources	→	88	100	57.1
4	GPT-4o	73.1	Data Confidence 95% 2 sources	→	75.4	100	85.7
5	Llama 3.3 70B	63	Data Confidence 60% 1 sources	→	87.2	100	0
6	Qwen2.5 72B	62.6	Data Confidence 60% 1 sources	→	86	100	0
7	Gemini 1.5 Flash	60.9	Data Confidence 60% 1 sources	→	75.3	100	0
8	Claude 3 Opus	60.3	Data Confidence 60% 1 sources	→	74	100	0
9	GLM-4	60.1	Data Confidence 60% 1 sources	→	80.8	100	0
10	DeepSeek V3	59.4	Data Confidence 60% 1 sources	→	85.6	100	0
11	Llama 3.1 405B	58.1	Data Confidence 60% 1 sources	→	76.2	100	0
12	GPT-4o mini	55.1	Data Confidence 95% 2 sources	→	69.7	100	0
13	DeepSeek R1	55	Data Confidence 60% 1 sources	→	75.7	100	0
14	Claude 3 Haiku	54.6	Data Confidence 60% 1 sources	→	61.4	100	0
15	Gemini 2.0 Flash	47.5	Data Confidence 95% 1 sources	→	0	100	100
16	Gemini 2.5 Flash	47.5	Data Confidence 95% 1 sources	→	0	100	100
17	Gemini 2.5 Pro	47.5	Data Confidence 95% 1 sources	→	0	100	100
18	Gemini 3 Flash	47.5	Data Confidence 95% 0 sources	→	0	100	100
19	Gemini 3.1 Pro	47.5	Data Confidence 95% 0 sources	→	0	100	100
20	Claude 3.7 Sonnet	44.8	Data Confidence 95% 1 sources	→	0	100	85.7
21	Claude Haiku 4.5	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
22	Claude Opus 4	44.8	Data Confidence 95% 1 sources	→	0	100	85.7
23	Claude Opus 4.8	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
24	Claude Opus 5	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
25	Claude Sonnet 4	44.8	Data Confidence 95% 1 sources	→	0	100	85.7
26	Claude Sonnet 4.6	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
27	Claude Sonnet 5	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
28	Gemini 2.5 Flash-Lite	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
29	Gemini 3.1 Flash-Lite	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
30	Llama 4 Maverick	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
31	Llama 4 Scout	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
32	GPT-4.1	44.8	Data Confidence 95% 1 sources	→	0	100	85.7
33	GPT-4.1 mini	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
34	GPT-4.1 nano	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
35	GPT-5.4	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
36	GPT-5.5	44.8	Data Confidence 95% 0 sources	→	0	100	85.7
37	o3	39.4	Data Confidence 95% 0 sources	→	0	100	57.1
38	o4-mini	39.4	Data Confidence 95% 0 sources	→	0	100	57.1
39	Claude Haiku 3.5	28.5	Data Confidence 95% 1 sources	→	0	100	0
40	MiniMax M3	23.6	Data Confidence 50% 0 sources	→	0	100	85.7
41	Grok 4	23.6	Data Confidence 50% 0 sources	→	0	100	85.7
42	GLM-4.6	23.6	Data Confidence 50% 0 sources	→	0	100	85.7
43	ERNIE 4.5 VL 424B	21.6	Data Confidence 50% 0 sources	→	0	100	85.7
44	Qwen3 Coder 480B	20.7	Data Confidence 50% 0 sources	→	0	100	57.1
45	Doubao 1.5 Pro	20.7	Data Confidence 50% 0 sources	→	0	100	57.1
46	DeepSeek V4-Flash	20.7	Data Confidence 50% 0 sources	→	0	100	57.1
47	DeepSeek V4-Pro	20.7	Data Confidence 50% 0 sources	→	0	100	57.1
48	Kimi K2.5	20.7	Data Confidence 50% 0 sources	→	0	100	57.1
49	Kimi K2.6	20.7	Data Confidence 50% 0 sources	→	0	100	57.1
50	Hunyuan TurboS	20.7	Data Confidence 50% 0 sources	→	0	100	57.1
51	GLM-4.5	20.3	Data Confidence 50% 1 sources	→	0	100	71.4
52	Qwen3 235B	19	Data Confidence 50% 1 sources	→	0	100	57.1
53	Qwen3 32B	19	Data Confidence 50% 0 sources	→	0	100	57.1
54	Kimi K2	19	Data Confidence 50% 1 sources	→	0	100	57.1
55	Mistral Large 3	18.9	Data Confidence 50% 0 sources	→	0	100	57.1
56	Mistral Small 4	18.9	Data Confidence 50% 0 sources	→	0	100	57.1
57	Qwen3 Coder 30B	18	Data Confidence 60% 0 sources	→	0	100	0
58	Claude 2.1	18	Data Confidence 60% 0 sources	→	0	100	0
59	Claude 3.5 Haiku	18	Data Confidence 60% 0 sources	→	0	100	0
60	Doubao 1.5 Lite	18	Data Confidence 60% 0 sources	→	0	100	0
61	Gemini 2.0 Pro	18	Data Confidence 60% 0 sources	→	0	100	0
62	Gemini 3 Flash Lite	18	Data Confidence 60% 0 sources	→	0	100	0
63	Gemini 3 Nano	18	Data Confidence 60% 0 sources	→	0	100	0
64	Llama 4 Behemoth	18	Data Confidence 60% 0 sources	→	0	100	0
65	MiniMax M1	18	Data Confidence 60% 0 sources	→	0	100	0
66	MiniMax M2	18	Data Confidence 60% 0 sources	→	0	100	0
67	MiniMax Text-01	18	Data Confidence 60% 0 sources	→	0	100	0
68	Kimi K1.5 Long	18	Data Confidence 60% 0 sources	→	0	100	0
69	GPT-5	18	Data Confidence 60% 0 sources	→	0	100	0
70	GPT-5.1	18	Data Confidence 60% 0 sources	→	0	100	0
71	o3-mini	18	Data Confidence 60% 0 sources	→	0	100	0
72	DeepSeek Chat	17.5	Data Confidence 50% 1 sources	→	0	100	42.9
73	DeepSeek Reasoner	17.5	Data Confidence 50% 1 sources	→	0	100	42.9
74	Qwen2.5 14B	15.9	Data Confidence 60% 0 sources	→	0	100	0
75	Qwen2.5 Coder 32B	15.9	Data Confidence 60% 0 sources	→	0	100	0
76	Qwen3 30B	15.9	Data Confidence 60% 0 sources	→	0	100	0
77	Qwen3 480B	15.9	Data Confidence 60% 0 sources	→	0	100	0
78	ERNIE 4.5	15.9	Data Confidence 60% 0 sources	→	0	100	0
79	Kimi K1.5	15.9	Data Confidence 60% 0 sources	→	0	100	0
80	Kimi K2 Turbo	15.9	Data Confidence 60% 0 sources	→	0	100	0
81	Hunyuan Lite	15.9	Data Confidence 60% 0 sources	→	0	100	0
82	Hunyuan T1	15.9	Data Confidence 60% 0 sources	→	0	100	0
83	Grok 3	15.9	Data Confidence 60% 0 sources	→	0	100	0
84	Grok 3 Mini	15.9	Data Confidence 60% 0 sources	→	0	100	0
85	DeepSeek Coder V2	15.8	Data Confidence 60% 0 sources	→	0	100	0
86	DeepSeek V2.5	15.8	Data Confidence 60% 0 sources	→	0	100	0
87	DeepSeek V3.1	15.8	Data Confidence 60% 0 sources	→	0	100	0
88	Llama 3.2 90B Vision	15.8	Data Confidence 60% 0 sources	→	0	100	0
89	GPT-4 Turbo	15.8	Data Confidence 60% 0 sources	→	0	100	0
90	GLM-4-Air	15.8	Data Confidence 60% 0 sources	→	0	100	0
91	Qwen-VL-Max	13	Data Confidence 60% 0 sources	→	0	100	0
92	Codestral 25.01	13	Data Confidence 60% 0 sources	→	0	100	0
93	Mistral 7B	13	Data Confidence 60% 0 sources	→	0	100	0
94	Mistral Small 3	13	Data Confidence 60% 0 sources	→	0	100	0
95	GPT-3.5 Turbo	12.5	Data Confidence 60% 0 sources	→	0	100	0
96	Kimi K3	6	Data Confidence 60% 0 sources	→	0	0	0
97	GLM-4.5-Plus	6	Data Confidence 60% 0 sources	→	0	0	0
98	GLM-5	6	Data Confidence 60% 0 sources	→	0	0	0
99	GLM-5.2	6	Data Confidence 60% 0 sources	→	0	0	0
100	GLM-4-Flash	3.8	Data Confidence 60% 0 sources	→	0	0	0

Related Models

Similar choices: Claude 3.5 Sonnet

Claude 3.7 Sonnet60%Claude Sonnet 460%Claude Sonnet 4.660%

Claude 3.5 Sonnet→78.4
Anthropic
Benchmark
80
Price Efficiency
100
Capability
85.7
Gemini 1.5 Pro→76.9
Google
Benchmark
70.8
Price Efficiency
100
Capability
100
Mistral Large 2→73.6
Mistral
Benchmark
88
Price Efficiency
100
Capability
57.1
GPT-4o→73.1
OpenAI
Benchmark
75.4
Price Efficiency
100
Capability
85.7
Llama 3.3 70B→63
Meta
Benchmark
87.2
Price Efficiency
100
Capability
0
Qwen2.5 72B→62.6
Alibaba
Benchmark
86
Price Efficiency
100
Capability
0
Gemini 1.5 Flash→60.9
Google
Benchmark
75.3
Price Efficiency
100
Capability
0
Claude 3 Opus→60.3
Anthropic
Benchmark
74
Price Efficiency
100
Capability
0
GLM-4→60.1
Zhipu
Benchmark
80.8
Price Efficiency
100
Capability
0
DeepSeek V3→59.4
DeepSeek
Benchmark
85.6
Price Efficiency
100
Capability
0
Llama 3.1 405B→58.1
Meta
Benchmark
76.2
Price Efficiency
100
Capability
0
GPT-4o mini→55.1
OpenAI
Benchmark
69.7
Price Efficiency
100
Capability
0
DeepSeek R1→55
DeepSeek
Benchmark
75.7
Price Efficiency
100
Capability
0
Claude 3 Haiku→54.6
Anthropic
Benchmark
61.4
Price Efficiency
100
Capability
0
Gemini 2.0 Flash→47.5
Google
Benchmark
0
Price Efficiency
100
Capability
100
Gemini 2.5 Flash→47.5
Google
Benchmark
0
Price Efficiency
100
Capability
100
Gemini 2.5 Pro→47.5
Google
Benchmark
0
Price Efficiency
100
Capability
100
Gemini 3 Flash→47.5
Google
Benchmark
0
Price Efficiency
100
Capability
100
Gemini 3.1 Pro→47.5
Google
Benchmark
0
Price Efficiency
100
Capability
100
Claude 3.7 Sonnet→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Haiku 4.5→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Opus 4→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Opus 4.8→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Opus 5→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Sonnet 4→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Sonnet 4.6→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Sonnet 5→44.8
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Gemini 2.5 Flash-Lite→44.8
Google
Benchmark
0
Price Efficiency
100
Capability
85.7
Gemini 3.1 Flash-Lite→44.8
Google
Benchmark
0
Price Efficiency
100
Capability
85.7
Llama 4 Maverick→44.8
Meta
Benchmark
0
Price Efficiency
100
Capability
85.7
Llama 4 Scout→44.8
Meta
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-4.1→44.8
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-4.1 mini→44.8
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-4.1 nano→44.8
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-5.4→44.8
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-5.5→44.8
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
o3→39.4
OpenAI
Benchmark
0
Price Efficiency
100
Capability
57.1
o4-mini→39.4
OpenAI
Benchmark
0
Price Efficiency
100
Capability
57.1
Claude Haiku 3.5→28.5
Anthropic
Benchmark
0
Price Efficiency
100
Capability
0
MiniMax M3→23.6
MiniMax
Benchmark
0
Price Efficiency
100
Capability
85.7
Grok 4→23.6
xAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GLM-4.6→23.6
Zhipu
Benchmark
0
Price Efficiency
100
Capability
85.7
ERNIE 4.5 VL 424B→21.6
Baidu
Benchmark
0
Price Efficiency
100
Capability
85.7
Qwen3 Coder 480B→20.7
Alibaba
Benchmark
0
Price Efficiency
100
Capability
57.1
Doubao 1.5 Pro→20.7
ByteDance
Benchmark
0
Price Efficiency
100
Capability
57.1
DeepSeek V4-Flash→20.7
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
57.1
DeepSeek V4-Pro→20.7
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
57.1
Kimi K2.5→20.7
Moonshot
Benchmark
0
Price Efficiency
100
Capability
57.1
Kimi K2.6→20.7
Moonshot
Benchmark
0
Price Efficiency
100
Capability
57.1
Hunyuan TurboS→20.7
Tencent
Benchmark
0
Price Efficiency
100
Capability
57.1
GLM-4.5→20.3
Zhipu
Benchmark
0
Price Efficiency
100
Capability
71.4
Qwen3 235B→19
Alibaba
Benchmark
0
Price Efficiency
100
Capability
57.1
Qwen3 32B→19
Alibaba
Benchmark
0
Price Efficiency
100
Capability
57.1
Kimi K2→19
Moonshot
Benchmark
0
Price Efficiency
100
Capability
57.1
Mistral Large 3→18.9
Mistral
Benchmark
0
Price Efficiency
100
Capability
57.1
Mistral Small 4→18.9
Mistral
Benchmark
0
Price Efficiency
100
Capability
57.1
Qwen3 Coder 30B→18
Alibaba
Benchmark
0
Price Efficiency
100
Capability
0
Claude 2.1→18
Anthropic
Benchmark
0
Price Efficiency
100
Capability
0
Claude 3.5 Haiku→18
Anthropic
Benchmark
0
Price Efficiency
100
Capability
0
Doubao 1.5 Lite→18
ByteDance
Benchmark
0
Price Efficiency
100
Capability
0
Gemini 2.0 Pro→18
Google
Benchmark
0
Price Efficiency
100
Capability
0
Gemini 3 Flash Lite→18
Google
Benchmark
0
Price Efficiency
100
Capability
0
Gemini 3 Nano→18
Google
Benchmark
0
Price Efficiency
100
Capability
0
Llama 4 Behemoth→18
Meta
Benchmark
0
Price Efficiency
100
Capability
0
MiniMax M1→18
MiniMax
Benchmark
0
Price Efficiency
100
Capability
0
MiniMax M2→18
MiniMax
Benchmark
0
Price Efficiency
100
Capability
0
MiniMax Text-01→18
MiniMax
Benchmark
0
Price Efficiency
100
Capability
0
Kimi K1.5 Long→18
Moonshot
Benchmark
0
Price Efficiency
100
Capability
0
GPT-5→18
OpenAI
Benchmark
0
Price Efficiency
100
Capability
0
GPT-5.1→18
OpenAI
Benchmark
0
Price Efficiency
100
Capability
0
o3-mini→18
OpenAI
Benchmark
0
Price Efficiency
100
Capability
0
DeepSeek Chat→17.5
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
42.9
DeepSeek Reasoner→17.5
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
42.9
Qwen2.5 14B→15.9
Alibaba
Benchmark
0
Price Efficiency
100
Capability
0
Qwen2.5 Coder 32B→15.9
Alibaba
Benchmark
0
Price Efficiency
100
Capability
0
Qwen3 30B→15.9
Alibaba
Benchmark
0
Price Efficiency
100
Capability
0
Qwen3 480B→15.9
Alibaba
Benchmark
0
Price Efficiency
100
Capability
0
ERNIE 4.5→15.9
Baidu
Benchmark
0
Price Efficiency
100
Capability
0
Kimi K1.5→15.9
Moonshot
Benchmark
0
Price Efficiency
100
Capability
0
Kimi K2 Turbo→15.9
Moonshot
Benchmark
0
Price Efficiency
100
Capability
0
Hunyuan Lite→15.9
Tencent
Benchmark
0
Price Efficiency
100
Capability
0
Hunyuan T1→15.9
Tencent
Benchmark
0
Price Efficiency
100
Capability
0
Grok 3→15.9
xAI
Benchmark
0
Price Efficiency
100
Capability
0
Grok 3 Mini→15.9
xAI
Benchmark
0
Price Efficiency
100
Capability
0
DeepSeek Coder V2→15.8
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
0
DeepSeek V2.5→15.8
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
0
DeepSeek V3.1→15.8
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
0
Llama 3.2 90B Vision→15.8
Meta
Benchmark
0
Price Efficiency
100
Capability
0
GPT-4 Turbo→15.8
OpenAI
Benchmark
0
Price Efficiency
100
Capability
0
GLM-4-Air→15.8
Zhipu
Benchmark
0
Price Efficiency
100
Capability
0
Qwen-VL-Max→13
Alibaba
Benchmark
0
Price Efficiency
100
Capability
0
Codestral 25.01→13
Mistral
Benchmark
0
Price Efficiency
100
Capability
0
Mistral 7B→13
Mistral
Benchmark
0
Price Efficiency
100
Capability
0
Mistral Small 3→13
Mistral
Benchmark
0
Price Efficiency
100
Capability
0
GPT-3.5 Turbo→12.5
OpenAI
Benchmark
0
Price Efficiency
100
Capability
0
Kimi K3→6
Moonshot
Benchmark
0
Price Efficiency
0
Capability
0
GLM-4.5-Plus→6
Zhipu
Benchmark
0
Price Efficiency
0
Capability
0
GLM-5→6
Zhipu
Benchmark
0
Price Efficiency
0
Capability
0
GLM-5.2→6
Zhipu
Benchmark
0
Price Efficiency
0
Capability
0
GLM-4-Flash→3.8
Zhipu
Benchmark
0
Price Efficiency
0
Capability
0

Compare Models →

Related Benchmarks

Coding Benchmark →Reasoning Benchmark →Math Benchmark →Vision Benchmark →