Model Comparison

Swipeer gives you access to the world's most powerful text models. Compare their verified performance benchmarks from Artificial Analysis.

Rank Model Name Intelligence Index Coding Index Agentic Index Pricing ($/1M tokens)
#01
GPT-5.4 (xhigh)*
OpenAI
57
57 69 $2.50 / $15.00
#02
Gemini 3.1 Pro Preview
Google DeepMind
57
56 59 $2.00 / $12.00
#03
Claude Sonnet 4.6 (max)*
Anthropic
52
51 63 $3.00 / $15.00
#04
GLM-5
Z.ai
50
44 63 $1.00 / $3.20
#05
MiniMax M2.7
MiniMax
50
42 61 $0.30 / $1.20
#06
GPT-5.4 Mini (xhigh)*
OpenAI
48
51 56 $0.75 / $4.50
#07
Grok 4.20 Beta
xAI
48
42 51 $2.00 / $6.00
#08
Gemini 3 Flash Preview
Google DeepMind
46
43 50 $0.50 / $3.00
#09
Qwen 3.5 397B A17B
Alibaba
45
41 56 $0.39 / $2.34
#10
GPT-5.4 Nano (xhigh)*
OpenAI
44
44 49 $0.20 / $1.25
#11
MiMo-V2-Flash
Xiaomi
41
33 49 $0.10 / $0.30
#12
Gemma 4 31B
Google DeepMind
39
39 41 $0.14 / $0.40
#13
Gemini 3.1 Flash-Lite
Google DeepMind
36
31 40 $0.25 / $1.50
#14
gpt-oss-120b (high)*
OpenAI (Open Weights)
33
29 38 $0.039 / $0.19
#15
Qwen 3.5 9B
Alibaba
32
31 37 $0.10 / $0.15
#16
DeepSeek V3.2 Speciale
DeepSeek
29
38 29 $0.27 / $0.41
#17
Mistral Small 2603
Mistral AI
27
24 22 $0.15 / $0.60
#18
Perplexity Sonar (web)
Perplexity AI
12
- - $1.00 / $1.00

* Represents the theoretical maximum intelligence at the highest reasoning level.

Benchmarks are updated regularly. Swipeer uses Artificial Analysis as source.