AI Model Picker

All Models

18 / 352

0(0–61)
0(0–59)
0.0(0.0–963.5)
$262.50($0.02–$262.50)
Updated Artificial Analysis

Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

Anthropic·5/27/26

Pricing (per 1M)

Input: $6.25
Output: $25.00

Speed

Output t/s: 59.8
TTFT: 12.48s

Benchmarks

Intelligence: 61.4Coding: 56.7GPQA: 92.0HLE: 45.7SCICODE: 53.5IFBENCH: 62.2LCR: 67.7TERMINALBENCH HARD: 58.3TAU2: 94.4

GPT-5.5 (xhigh)

OpenAI·4/24/26

Pricing (per 1M)

Input: $5.00
Output: $30.00

Speed

Output t/s: 69.5
TTFT: 37.98s

Benchmarks

Intelligence: 60.2Coding: 59.1GPQA: 93.5HLE: 44.3SCICODE: 56.1IFBENCH: 75.9LCR: 74.3TERMINALBENCH HARD: 60.6TAU2: 93.9

GPT-5.5 (high)

OpenAI·4/24/26

Pricing (per 1M)

Input: $5.00
Output: $30.00

Speed

Output t/s: 69.9
TTFT: 17.38s

Benchmarks

Intelligence: 58.9Coding: 58.5GPQA: 93.2HLE: 43.0SCICODE: 55.9IFBENCH: 71.6LCR: 73.3TERMINALBENCH HARD: 59.8TAU2: 93.0

Gemini 3.1 Pro Preview

Google·2/19/26

Pricing (per 1M)

Input: $2.00
Output: $12.00

Speed

Output t/s: 135.9
TTFT: 22.92s

Benchmarks

Intelligence: 57.2Coding: 55.5GPQA: 94.1HLE: 44.7SCICODE: 58.9IFBENCH: 77.1LCR: 72.7TERMINALBENCH HARD: 53.8TAU2: 95.6

GPT-5.4 (xhigh)

OpenAI·3/5/26

Pricing (per 1M)

Input: $2.50
Output: $15.00

Speed

Output t/s: 81.8
TTFT: 163.99s

Benchmarks

Intelligence: 56.8Coding: 57.2GPQA: 92.0HLE: 41.6SCICODE: 56.6IFBENCH: 73.9LCR: 74.0TERMINALBENCH HARD: 57.6TAU2: 87.1

Qwen3.7 Max

Alibaba·5/21/26

Pricing (per 1M)

Input: $2.50
Output: $7.50

Speed

Output t/s: 204.6
TTFT: 1.68s

Benchmarks

Intelligence: 56.6Coding: 50.1GPQA: 92.3HLE: 38.1SCICODE: 48.8IFBENCH: 80.5LCR: 69.0TERMINALBENCH HARD: 50.8TAU2: 94.7

Gemini 3.5 Flash (high)

Google·5/19/26

Pricing (per 1M)

Input: $1.50
Output: $9.00

Speed

Output t/s: 226.3
TTFT: 13.20s

Benchmarks

Intelligence: 55.3Coding: 45GPQA: 92.2HLE: 41.0SCICODE: 53.1IFBENCH: 76.3LCR: 69.3TERMINALBENCH HARD: 40.9TAU2: 95.3

MiMo-V2.5-Pro

Xiaomi·4/22/26

Pricing (per 1M)

Input: $0.43
Output: $0.87

Speed

Output t/s: 53.2
TTFT: 1.93s

Benchmarks

Intelligence: 53.8Coding: 45.5GPQA: 86.6HLE: 33.8SCICODE: 50.2IFBENCH: 79.9LCR: 73.3TERMINALBENCH HARD: 43.2TAU2: 94.2

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

Anthropic·2/17/26

Pricing (per 1M)

Input: $3.75
Output: $15.00

Speed

Output t/s: 63.9
TTFT: 70.80s

Benchmarks

Intelligence: 51.7Coding: 50.9GPQA: 87.5HLE: 30.0SCICODE: 46.8IFBENCH: 56.6LCR: 70.7TERMINALBENCH HARD: 53.0TAU2: 75.7

DeepSeek V4 Pro (Reasoning, Max Effort)

DeepSeek·4/24/26

Pricing (per 1M)

Input: $0.43
Output: $0.87

Speed

Output t/s: 53.6
TTFT: 1.19s

Benchmarks

Intelligence: 51.5Coding: 47.5GPQA: 88.8HLE: 35.9SCICODE: 50.0IFBENCH: 76.5LCR: 66.3TERMINALBENCH HARD: 46.2TAU2: 96.2

DeepSeek V4 Pro (Reasoning, High Effort)

DeepSeek·4/24/26

Pricing (per 1M)

Input: $0.43
Output: $0.87

Speed

Output t/s: 55.2
TTFT: 1.17s

Benchmarks

Intelligence: 49.8Coding: 43.2GPQA: 90.5HLE: 33.5SCICODE: 46.4IFBENCH: 71.3LCR: 65.0TERMINALBENCH HARD: 41.7TAU2: 94.2

MiMo-V2.5

Xiaomi·4/22/26

Pricing (per 1M)

Input: $0.14
Output: $0.28

Speed

Output t/s: 98.3
TTFT: 2.29s

Benchmarks

Intelligence: 49Coding: 42.1GPQA: 84.9HLE: 25.2SCICODE: 43.1IFBENCH: 67.1LCR: 62.7TERMINALBENCH HARD: 41.7TAU2: 90.6

GPT-5.4 (low)

OpenAI·3/5/26

Pricing (per 1M)

Input: $2.50
Output: $15.00

Speed

Output t/s: 67.2
TTFT: 1.67s

Benchmarks

Intelligence: 47.9Coding: 45.6GPQA: 87.1HLE: 28.9SCICODE: 50.3IFBENCH: 65.9LCR: 67.3TERMINALBENCH HARD: 43.2TAU2: 74.6

DeepSeek V4 Flash (Reasoning, Max Effort)

DeepSeek·4/24/26

Pricing (per 1M)

Input: $0.14
Output: $0.28

Speed

Output t/s: 146.3
TTFT: 0.80s

Benchmarks

Intelligence: 46.5Coding: 38.7GPQA: 89.4HLE: 32.1SCICODE: 44.9IFBENCH: 79.2LCR: 63.0TERMINALBENCH HARD: 35.6TAU2: 95.0

DeepSeek V4 Flash (Reasoning, High Effort)

DeepSeek·4/24/26

Pricing (per 1M)

Input: $0.14
Output: $0.28

Speed

Output t/s: 0.0
TTFT: 0.00s

Benchmarks

Intelligence: 46Coding: 39.8GPQA: 86.7HLE: 27.8SCICODE: 42.0IFBENCH: 73.5LCR: 62.7TERMINALBENCH HARD: 38.6TAU2: 95.6

Qwen3.5 4B (Reasoning)

Alibaba·3/10/26

Pricing (per 1M)

Input: $0.03
Output: $0.15

Speed

Output t/s: 188.6
TTFT: 0.23s

Benchmarks

Intelligence: 27.1Coding: 17.5GPQA: 77.1HLE: 7.8SCICODE: 16.1IFBENCH: 52.0LCR: 55.7TERMINALBENCH HARD: 18.2TAU2: 92.1

gpt-oss-20B (high)

OpenAI·8/5/25

Pricing (per 1M)

Input: $0.05
Output: $0.20

Speed

Output t/s: 266.6
TTFT: 0.45s

Benchmarks

Intelligence: 24.5Coding: 18.5Math: 89.3MMLU PRO: 74.8GPQA: 68.8HLE: 9.8LIVECODEBENCH: 77.7SCICODE: 34.4AIME 25: 89.3IFBENCH: 65.1LCR: 30.7TERMINALBENCH HARD: 10.6TAU2: 60.2

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

NVIDIA·12/14/25

Pricing (per 1M)

Input: $0.06
Output: $0.22

Speed

Output t/s: 139.2
TTFT: 1.05s

Benchmarks

Intelligence: 24.3Coding: 19Math: 91MMLU PRO: 79.4GPQA: 75.7HLE: 10.2LIVECODEBENCH: 74.1SCICODE: 29.6AIME 25: 91.0IFBENCH: 71.1LCR: 33.7TERMINALBENCH HARD: 13.6TAU2: 40.9