Model Comparison

Comprehensive side-by-side analysis of model capabilities and performance

Qwen2.5 72B Instruct

Alibaba

Qwen2.5 72B Instruct is a language model developed by Alibaba. It achieves strong performance with an average score of 77.4% across 14 benchmarks. It excels particularly in GSM8k (95.8%), MT-Bench (93.5%), MBPP (88.2%). The model shows particular specialization in math tasks with an average performance of 89.5%. It supports a 139K token context window for handling large documents. The model is available through 4 API providers. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Alibaba's latest advancement in AI technology.

QwQ-32B-Preview

Alibaba

QwQ-32B-Preview is a language model developed by Alibaba. It achieves strong performance with an average score of 64.0% across 4 benchmarks. It excels particularly in MATH-500 (90.6%), GPQA (65.2%), AIME 2024 (50.0%). The model is available through 4 API providers. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Alibaba's latest advancement in AI technology.

Qwen2.5 72B Instruct

Alibaba

2024-09-19

QwQ-32B-Preview

Alibaba

2024-11-28

2 months newer

Pricing Comparison

Cost per million tokens (USD)

Qwen2.5 72B Instruct

Input:$0.35

Output:$0.40

QwQ-32B-Preview

$0.40 cheaper

Input:$0.15

Output:$0.20

Performance Metrics

Context window and performance specifications

Qwen2.5 72B Instruct

Larger context

Max Context:139.3K

Parameters:72.7B

QwQ-32B-Preview

Max Context:65.5K

Parameters:32.5B

Average performance across 2 common benchmarks

Qwen2.5 72B Instruct

Average Score:52.3%

QwQ-32B-Preview

+5.4%

Average Score:57.6%

Performance comparison across key benchmark categories

Qwen2.5 72B Instruct

math

89.5%

code

+28.6%

78.6%

general

+16.5%

74.1%

QwQ-32B-Preview

math

+1.2%

90.6%

code

50.0%

general

57.6%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Knowledge Cutoff

Training data recency comparison

QwQ-32B-Preview

2024-11-28

More recent knowledge cutoff means awareness of newer technologies and frameworks

Provider Availability & Performance

Available providers and their performance metrics

Qwen2.5 72B Instruct

4 providers

Together

Throughput: 47 tok/s

Latency: 0.5ms

Hyperbolic

Throughput: 100 tok/s

Latency: 0.5ms

DeepInfra

Throughput: 10 tok/s

Latency: 0.5ms

Fireworks

Throughput: 59 tok/s

Latency: 0.37ms

QwQ-32B-Preview

4 providers

Together

Throughput: 62.14 tok/s

Latency: 0.74ms

Hyperbolic

Throughput: 31.9 tok/s

Latency: 1.05ms

DeepInfra

Throughput: 76.04 tok/s

Latency: 0.44ms

Fireworks

Throughput: 99.15 tok/s

Latency: 0.53ms

Qwen2.5 72B Instruct

Avg Score:52.3%

Providers:4

QwQ-32B-Preview

+5.4%

Avg Score:57.6%

Providers:4