AI Model Picker

Model Suggestions

Updated Artificial Analysis

Best for General Use (Balanced)

GPT-5.6 Luna (max)

OpenAI·7/9/26

Score: 63.9

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 163.1
TTFT: 57.45s

Benchmarks

Intelligence: 52.3Coding: 71.4GPQA: 91.1HLE: 39.5SCICODE: 52.5LCR: 78.3TERMINALBENCH V2 1: 80.9TAU BANKING: 31.1

Muse Spark 1.1 (xhigh)

Meta·7/16/26

Score: 62.8

Pricing (per 1M)

Input: $1.25
Output: $4.25

Speed

Output t/s: 190.7
TTFT: 0.00s

Benchmarks

Intelligence: 53.2Coding: 71.3GPQA: 89.8HLE: 46.2SCICODE: 58.2LCR: 81.3TERMINALBENCH V2 1: 77.9TAU BANKING: 31.8

GPT-5.6 Luna (xhigh)

OpenAI·7/9/26

Score: 62.0

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 157.5
TTFT: 30.84s

Benchmarks

Intelligence: 50.1Coding: 68.6GPQA: 89.5HLE: 37.0SCICODE: 50.0LCR: 73.3TERMINALBENCH V2 1: 77.9TAU BANKING: 28.7
#4
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
DeepSeek
Score: 61.6
#5
Gemini 3.6 Flash (high)
Google
Score: 60.1
#6
GPT-5.6 Luna (high)
OpenAI
Score: 59.9

Best for Coding Tools

GPT-5.6 Terra (max)

OpenAI·7/9/26

Score: 74.8

Pricing (per 1M)

Input: $2.00
Output: $12.00

Speed

Output t/s: 121.3
TTFT: 75.46s

Benchmarks

Intelligence: 56.6Coding: 76.7GPQA: 92.5HLE: 42.9SCICODE: 53.9IFBENCH: 71.2LCR: 79.7TERMINALBENCH HARD: 57.6TERMINALBENCH V2 1: 88.0TAU2: 86.3TAU BANKING: 40.2

GPT-5.6 Luna (max)

OpenAI·7/9/26

Score: 73.1

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 163.1
TTFT: 57.45s

Benchmarks

Intelligence: 52.3Coding: 71.4GPQA: 91.1HLE: 39.5SCICODE: 52.5LCR: 78.3TERMINALBENCH V2 1: 80.9TAU BANKING: 31.1

Muse Spark 1.1 (xhigh)

Meta·7/16/26

Score: 72.9

Pricing (per 1M)

Input: $1.25
Output: $4.25

Speed

Output t/s: 190.7
TTFT: 0.00s

Benchmarks

Intelligence: 53.2Coding: 71.3GPQA: 89.8HLE: 46.2SCICODE: 58.2LCR: 81.3TERMINALBENCH V2 1: 77.9TAU BANKING: 31.8
#4
GPT-5.6 Sol (xhigh)
OpenAI
Score: 72.1
#5
Kimi K3 (max)
Kimi
Score: 71.6
#6
Claude Opus 5 (Adaptive Reasoning, Max Effort)
Anthropic
Score: 71.5

Best Value (Cost Efficient)

GPT-5.6 Luna (max)

OpenAI·7/9/26

Score: 68.9

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 163.1
TTFT: 57.45s

Benchmarks

Intelligence: 52.3Coding: 71.4GPQA: 91.1HLE: 39.5SCICODE: 52.5LCR: 78.3TERMINALBENCH V2 1: 80.9TAU BANKING: 31.1

DeepSeek V4 Flash 0731 (Reasoning, Max Effort)

DeepSeek·7/31/26

Score: 68.3

Pricing (per 1M)

Input: $0.14
Output: $0.28

Speed

Output t/s: 113.2
TTFT: 0.99s

Benchmarks

Intelligence: 51.8Coding: 69.1GPQA: 90.8HLE: 38.6SCICODE: 49.9LCR: 74.3TERMINALBENCH V2 1: 78.7TAU BANKING: 39.4

GPT-5.6 Luna (xhigh)

OpenAI·7/9/26

Score: 67.4

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 157.5
TTFT: 30.84s

Benchmarks

Intelligence: 50.1Coding: 68.6GPQA: 89.5HLE: 37.0SCICODE: 50.0LCR: 73.3TERMINALBENCH V2 1: 77.9TAU BANKING: 28.7
#4
GPT-5.6 Luna (high)
OpenAI
Score: 65.6
#5
Muse Spark 1.1 (xhigh)
Meta
Score: 64.7
#6
MiniMax-M3
MiniMax
Score: 62.8

Smart & Fast (Intel > Speed > Price)

Muse Spark 1.1 (xhigh)

Meta·7/16/26

Score: 58.8

Pricing (per 1M)

Input: $1.25
Output: $4.25

Speed

Output t/s: 190.7
TTFT: 0.00s

Benchmarks

Intelligence: 53.2Coding: 71.3GPQA: 89.8HLE: 46.2SCICODE: 58.2LCR: 81.3TERMINALBENCH V2 1: 77.9TAU BANKING: 31.8

Gemini 3.5 Flash (high)

Google·5/19/26

Score: 57.5

Pricing (per 1M)

Input: $1.50
Output: $9.00

Speed

Output t/s: 271.7
TTFT: 0.00s

Benchmarks

Intelligence: 52Coding: 70.1GPQA: 92.2HLE: 42.7SCICODE: 53.1IFBENCH: 76.3LCR: 81.0TERMINALBENCH HARD: 40.9TERMINALBENCH V2 1: 78.7TAU2: 95.3TAU BANKING: 32.2

GPT-5.6 Luna (max)

OpenAI·7/9/26

Score: 57.4

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 163.1
TTFT: 57.45s

Benchmarks

Intelligence: 52.3Coding: 71.4GPQA: 91.1HLE: 39.5SCICODE: 52.5LCR: 78.3TERMINALBENCH V2 1: 80.9TAU BANKING: 31.1
#4
Gemini 3.6 Flash (high)
Google
Score: 57.3
#5
GPT-5.6 Terra (max)
OpenAI
Score: 56.9
#6
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
Anthropic
Score: 56.2