Model Comparison

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

Mistral Large 2

Mistral AI

Mistral Large 2 is a language model developed by Mistral AI. This model demonstrates exceptional performance with an average score of 87.6% across 5 benchmarks. It excels particularly in GSM8k (93.0%), HumanEval (92.0%), MT-Bench (86.3%). It supports a 256K token context window for handling large documents. The model is available through 2 API providers. Released in 2024, it represents Mistral AI's latest advancement in AI technology.

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.

Mistral Large 2

Mistral AI

2024-07-24

Qwen2.5 72B Instruct

Alibaba

2024-09-19

1 month newer

Pricing Comparison

Cost per million tokens (USD)

Mistral Large 2

Input:$2.00

Output:$6.00

Qwen2.5 72B Instruct

$7.25 cheaper

Input:$0.35

Output:$0.40

Performance Metrics

Context window and performance specifications

Mistral Large 2

Larger context

Max Context:256.0K

Parameters:123.0B

Qwen2.5 72B Instruct

Max Context:139.3K

Parameters:72.7B

Average performance across 3 common benchmarks

Mistral Large 2

Average Score:90.4%

Qwen2.5 72B Instruct

+1.5%

Average Score:92.0%

Performance comparison across key benchmark categories

Mistral Large 2

math

+3.5%

93.0%

code

+13.4%

92.0%

roleplay

+13.4%

86.3%

general

+9.3%

83.4%

Qwen2.5 72B Instruct

math

89.5%

code

78.6%

roleplay

72.9%

general

74.1%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Provider Availability & Performance

Available providers and their performance metrics

Mistral Large 2

2 providers

Google

Throughput: 42 tok/s

Latency: 0.4ms

Mistral AI

Throughput: 0.1 tok/s

Latency: 0.5ms

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

Mistral Large 2

Avg Score:90.4%

Providers:2

Qwen2.5 72B Instruct

+1.5%

Avg Score:92.0%

Providers:4