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	Rank Change	Benchmark	Price Efficiency	Capability
1	Gemini 2.5 Pro	96.1	→	92.3	100	100
2	Claude Opus 4	93.6	→	93	100	85.7
3	Gemini 2.5 Flash	93.3	→	86.7	100	100
4	GPT-4.1	92.5	→	90.7	100	85.7
5	Claude Sonnet 4	92.1	→	90	100	85.7
6	GPT-4o	88.5	→	90	100	85.7
7	o3	87.9	→	93	100	57.1
8	DeepSeek Reasoner	79.6	→	89.3	100	42.9
9	DeepSeek Chat	77.5	→	85	100	42.9
10	Gemini 1.5 Pro	50	→	0	100	100
11	Gemini 2.0 Flash	50	→	0	100	100
12	Gemini 3 Flash	50	→	0	100	100
13	Gemini 3.1 Pro	50	→	0	100	100
14	Claude 3.5 Sonnet	47.1	→	0	100	85.7
15	Claude 3.7 Sonnet	47.1	→	0	100	85.7
16	Claude Haiku 4.5	47.1	→	0	100	85.7
17	Claude Opus 4.8	47.1	→	0	100	85.7
18	Claude Opus 5	47.1	→	0	100	85.7
19	Claude Sonnet 4.6	47.1	→	0	100	85.7
20	Claude Sonnet 5	47.1	→	0	100	85.7
21	Gemini 2.5 Flash-Lite	47.1	→	0	100	85.7
22	Gemini 3.1 Flash-Lite	47.1	→	0	100	85.7
23	Llama 4 Maverick	47.1	→	0	100	85.7
24	Llama 4 Scout	47.1	→	0	100	85.7
25	MiniMax M3	47.1	→	0	100	85.7
26	GPT-4.1 mini	47.1	→	0	100	85.7
27	GPT-4.1 nano	47.1	→	0	100	85.7
28	GPT-5.4	47.1	→	0	100	85.7
29	GPT-5.5	47.1	→	0	100	85.7
30	Grok 4	47.1	→	0	100	85.7
31	GLM-4.6	47.1	→	0	100	85.7
32	ERNIE 4.5 VL 424B	43.3	→	0	100	85.7
33	Qwen3 Coder 480B	41.4	→	0	100	57.1
34	Doubao 1.5 Pro	41.4	→	0	100	57.1
35	DeepSeek V4-Flash	41.4	→	0	100	57.1
36	DeepSeek V4-Pro	41.4	→	0	100	57.1
37	Kimi K2.5	41.4	→	0	100	57.1
38	Kimi K2.6	41.4	→	0	100	57.1
39	o4-mini	41.4	→	0	100	57.1
40	Hunyuan TurboS	41.4	→	0	100	57.1
41	GLM-4.5	40.7	→	0	100	71.4
42	Qwen3 235B	38	→	0	100	57.1
43	Qwen3 32B	38	→	0	100	57.1
44	Kimi K2	38	→	0	100	57.1
45	Mistral Large 2	37.8	→	0	100	57.1
46	Mistral Large 3	37.8	→	0	100	57.1
47	Mistral Small 4	37.8	→	0	100	57.1
48	Claude Haiku 3.5	30	→	0	100	0
49	GPT-4o mini	26.4	→	0	100	0

Gemini 2.5 Pro→96.1
Google
Benchmark
92.3
Price Efficiency
100
Capability
100
Claude Opus 4→93.6
Anthropic
Benchmark
93
Price Efficiency
100
Capability
85.7
Gemini 2.5 Flash→93.3
Google
Benchmark
86.7
Price Efficiency
100
Capability
100
GPT-4.1→92.5
OpenAI
Benchmark
90.7
Price Efficiency
100
Capability
85.7
Claude Sonnet 4→92.1
Anthropic
Benchmark
90
Price Efficiency
100
Capability
85.7
GPT-4o→88.5
OpenAI
Benchmark
90
Price Efficiency
100
Capability
85.7
o3→87.9
OpenAI
Benchmark
93
Price Efficiency
100
Capability
57.1
DeepSeek Reasoner→79.6
DeepSeek
Benchmark
89.3
Price Efficiency
100
Capability
42.9
DeepSeek Chat→77.5
DeepSeek
Benchmark
85
Price Efficiency
100
Capability
42.9
Gemini 1.5 Pro→50
Google
Benchmark
0
Price Efficiency
100
Capability
100
Gemini 2.0 Flash→50
Google
Benchmark
0
Price Efficiency
100
Capability
100
Gemini 3 Flash→50
Google
Benchmark
0
Price Efficiency
100
Capability
100
Gemini 3.1 Pro→50
Google
Benchmark
0
Price Efficiency
100
Capability
100
Claude 3.5 Sonnet→47.1
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude 3.7 Sonnet→47.1
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Haiku 4.5→47.1
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Opus 4.8→47.1
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Opus 5→47.1
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Sonnet 4.6→47.1
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Claude Sonnet 5→47.1
Anthropic
Benchmark
0
Price Efficiency
100
Capability
85.7
Gemini 2.5 Flash-Lite→47.1
Google
Benchmark
0
Price Efficiency
100
Capability
85.7
Gemini 3.1 Flash-Lite→47.1
Google
Benchmark
0
Price Efficiency
100
Capability
85.7
Llama 4 Maverick→47.1
Meta
Benchmark
0
Price Efficiency
100
Capability
85.7
Llama 4 Scout→47.1
Meta
Benchmark
0
Price Efficiency
100
Capability
85.7
MiniMax M3→47.1
MiniMax
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-4.1 mini→47.1
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-4.1 nano→47.1
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-5.4→47.1
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GPT-5.5→47.1
OpenAI
Benchmark
0
Price Efficiency
100
Capability
85.7
Grok 4→47.1
xAI
Benchmark
0
Price Efficiency
100
Capability
85.7
GLM-4.6→47.1
Zhipu
Benchmark
0
Price Efficiency
100
Capability
85.7
ERNIE 4.5 VL 424B→43.3
Baidu
Benchmark
0
Price Efficiency
100
Capability
85.7
Qwen3 Coder 480B→41.4
Alibaba
Benchmark
0
Price Efficiency
100
Capability
57.1
Doubao 1.5 Pro→41.4
ByteDance
Benchmark
0
Price Efficiency
100
Capability
57.1
DeepSeek V4-Flash→41.4
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
57.1
DeepSeek V4-Pro→41.4
DeepSeek
Benchmark
0
Price Efficiency
100
Capability
57.1
Kimi K2.5→41.4
Moonshot
Benchmark
0
Price Efficiency
100
Capability
57.1
Kimi K2.6→41.4
Moonshot
Benchmark
0
Price Efficiency
100
Capability
57.1
o4-mini→41.4
OpenAI
Benchmark
0
Price Efficiency
100
Capability
57.1
Hunyuan TurboS→41.4
Tencent
Benchmark
0
Price Efficiency
100
Capability
57.1
GLM-4.5→40.7
Zhipu
Benchmark
0
Price Efficiency
100
Capability
71.4
Qwen3 235B→38
Alibaba
Benchmark
0
Price Efficiency
100
Capability
57.1
Qwen3 32B→38
Alibaba
Benchmark
0
Price Efficiency
100
Capability
57.1
Kimi K2→38
Moonshot
Benchmark
0
Price Efficiency
100
Capability
57.1
Mistral Large 2→37.8
Mistral
Benchmark
0
Price Efficiency
100
Capability
57.1
Mistral Large 3→37.8
Mistral
Benchmark
0
Price Efficiency
100
Capability
57.1
Mistral Small 4→37.8
Mistral
Benchmark
0
Price Efficiency
100
Capability
57.1
Claude Haiku 3.5→30
Anthropic
Benchmark
0
Price Efficiency
100
Capability
0
GPT-4o mini→26.4
OpenAI
Benchmark
0
Price Efficiency
100
Capability
0

Compare Models →