AI Model Picker

Model Suggestions

Updated Artificial Analysis

Best for General Use (Balanced)

Claude Haiku 5.5 (Max)

Anthropic·10/7/26

Score: 60.0

Pricing (per 1M)

Input: $0.10
Output: $0.50

Speed

Output t/s: 237.0
TTFT: 280.49s

Benchmarks

Intelligence: 43.4HLE: 44.4SCICODE: 55.0LCR: 82.7TERMINALBENCH V4 0: 32.8

Claude Sonnet 5.5 (Max, Default Fallback)

Anthropic·9/28/26

Score: 58.0

Pricing (per 1M)

Input: $2.00
Output: $10.00

Speed

Output t/s: 136.8
TTFT: 310.00s

Benchmarks

Intelligence: 56HLE: 55.0SCICODE: 61.0LCR: 82.7TERMINALBENCH V4 0: 63.6

Ling 3.1 Flash

InclusionAI·10/2/26

Score: 57.9

Pricing (per 1M)

Input: $0.30
Output: $0.90

Speed

Output t/s: 217.4
TTFT: 1.12s

Benchmarks

Intelligence: 41.1HLE: 39.4SCICODE: 54.1LCR: 83.0TERMINALBENCH V4 0: 33.3
#4
Muse Spark 1.3 (Xhigh)
Meta
Score: 57.6
#5
Claude Haiku 5.5 (Xhigh)
Anthropic
Score: 57.3
#6
DeepSeek V4.1 Flash (Max)
DeepSeek
Score: 56.6

Best for Coding Tools

Muse Spark 1.3 (Xhigh)

Meta·9/2/26

Score: 77.9

Pricing (per 1M)

Input: $1.25
Output: $4.25

Speed

Output t/s: 224.2
TTFT: 18.81s

Benchmarks

Intelligence: 45.1Coding: 76.5GPQA: 94.1HLE: 47.5SCICODE: 59.7LCR: 83.0TERMINALBENCH V2 1: 85.4TERMINALBENCH V4 0: 16.7TAU BANKING: 47.2

Gemini 3.8 Flash (High)

Google·9/2/26

Score: 76.2

Pricing (per 1M)

Input: $0.75
Output: $3.75

Speed

Output t/s: 130.8
TTFT: 15.46s

Benchmarks

Intelligence: 40.9Coding: 76.3GPQA: 95.3HLE: 47.8SCICODE: 56.6LCR: 81.3TERMINALBENCH V2 1: 87.6TERMINALBENCH V4 0: 19.7TAU BANKING: 44.9

Gemini 3.8 Flash (Medium)

Google·9/2/26

Score: 75.9

Pricing (per 1M)

Input: $0.75
Output: $3.75

Speed

Output t/s: 237.7
TTFT: 0.00s

Benchmarks

Intelligence: 39.8Coding: 74.1GPQA: 93.5HLE: 42.1SCICODE: 55.1LCR: 84.0TERMINALBENCH V2 1: 83.9TERMINALBENCH V4 0: 19.7TAU BANKING: 45.8
#4
Gemini 3.8 Flash (Low)
Google
Score: 75.4
#5
Claude Fable 5.1 (Max, Default Fallback)
Anthropic
Score: 75.2
#6
Muse Spark 1.3 (Max)
Meta
Score: 75.1

Best Value (Cost Efficient)

Claude Haiku 5.5 (Max)

Anthropic·10/7/26

Score: 65.3

Pricing (per 1M)

Input: $0.10
Output: $0.50

Speed

Output t/s: 237.0
TTFT: 280.49s

Benchmarks

Intelligence: 43.4HLE: 44.4SCICODE: 55.0LCR: 82.7TERMINALBENCH V4 0: 32.8

Claude Haiku 5.5 (Xhigh)

Anthropic·10/7/26

Score: 63.5

Pricing (per 1M)

Input: $0.10
Output: $0.50

Speed

Output t/s: 177.5
TTFT: 42.99s

Benchmarks

Intelligence: 41.2HLE: 42.7SCICODE: 51.7LCR: 78.3TERMINALBENCH V4 0: 29.3

Ling 3.1 Flash

InclusionAI·10/2/26

Score: 63.1

Pricing (per 1M)

Input: $0.30
Output: $0.90

Speed

Output t/s: 217.4
TTFT: 1.12s

Benchmarks

Intelligence: 41.1HLE: 39.4SCICODE: 54.1LCR: 83.0TERMINALBENCH V4 0: 33.3
#4
DeepSeek V4.1 Flash (Max)
DeepSeek
Score: 61.9
#5
MiMo-V2.6-Pro
Xiaomi
Score: 61.8
#6
Claude Haiku 5.5 (High)
Anthropic
Score: 61.0

Smart & Fast (Intel > Speed > Price)

Claude Sonnet 5.5 (Max, Default Fallback)

Anthropic·9/28/26

Score: 57.4

Pricing (per 1M)

Input: $2.00
Output: $10.00

Speed

Output t/s: 136.8
TTFT: 310.00s

Benchmarks

Intelligence: 56HLE: 55.0SCICODE: 61.0LCR: 82.7TERMINALBENCH V4 0: 63.6

Claude Opus 5.5 (Max, Default Fallback)

Anthropic·9/22/26

Score: 54.8

Pricing (per 1M)

Input: $4.00
Output: $20.00

Speed

Output t/s: 97.4
TTFT: 580.60s

Benchmarks

Intelligence: 57.6HLE: 61.4SCICODE: 66.9LCR: 84.7TERMINALBENCH V4 0: 59.6

Claude Opus 5.5 (Xhigh, Default Fallback)

Anthropic·9/22/26

Score: 52.5

Pricing (per 1M)

Input: $4.00
Output: $20.00

Speed

Output t/s: 78.7
TTFT: 64.26s

Benchmarks

Intelligence: 56HLE: 57.5SCICODE: 65.0LCR: 84.7TERMINALBENCH V4 0: 59.6
#4
Muse Spark 1.3 (Xhigh)
Meta
Score: 52.3
#5
Claude Sonnet 5.5 (Xhigh, Default Fallback)
Anthropic
Score: 51.9
#6
Claude Haiku 5.5 (Max)
Anthropic
Score: 51.8