Model Comparison

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

DeepSeek R1 Distill Llama 70B

DeepSeek

DeepSeek R1 Distill Llama 70B is a language model developed by DeepSeek. It achieves strong performance with an average score of 76.0% across 4 benchmarks. It excels particularly in MATH-500 (94.5%), AIME 2024 (86.7%), GPQA (65.2%). It supports a 256K token context window for handling large documents. The model is available through 1 API provider. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents DeepSeek's latest advancement in AI technology.

DeepSeek R1 Distill Qwen 32B

DeepSeek

DeepSeek R1 Distill Qwen 32B is a language model developed by DeepSeek. It achieves strong performance with an average score of 74.2% across 4 benchmarks. It excels particularly in MATH-500 (94.3%), AIME 2024 (83.3%), GPQA (62.1%). It supports a 256K token context window for handling large documents. The model is available through 1 API provider. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents DeepSeek's latest advancement in AI technology.

DeepSeek R1 Distill Llama 70B

DeepSeek

2025-01-20

DeepSeek R1 Distill Qwen 32B

DeepSeek

2025-01-20

0 days newer

Pricing Comparison

Cost per million tokens (USD)

DeepSeek R1 Distill Llama 70B

Input:$0.10

Output:$0.40

DeepSeek R1 Distill Qwen 32B

$0.20 cheaper

Input:$0.12

Output:$0.18

Performance Metrics

Context window and performance specifications

DeepSeek R1 Distill Llama 70B

Max Context:256.0K

Parameters:70.6B

DeepSeek R1 Distill Qwen 32B

Max Context:256.0K

Parameters:32.8B

Average performance across 4 common benchmarks

DeepSeek R1 Distill Llama 70B

+1.8%

Average Score:76.0%

DeepSeek R1 Distill Qwen 32B

Average Score:74.2%

Performance comparison across key benchmark categories

DeepSeek R1 Distill Llama 70B

math

+0.2%

94.5%

general

+3.3%

76.0%

code

+0.3%

57.5%

DeepSeek R1 Distill Qwen 32B

math

94.3%

general

72.7%

code

57.2%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Provider Availability & Performance

Available providers and their performance metrics

DeepSeek R1 Distill Llama 70B

1 providers

DeepInfra

Throughput: 37 tok/s

Latency: 0.65ms

DeepSeek R1 Distill Qwen 32B

1 providers

DeepInfra

Throughput: 37 tok/s

Latency: 0.65ms

DeepSeek R1 Distill Llama 70B

+1.8%

Avg Score:76.0%

Providers:1

DeepSeek R1 Distill Qwen 32B

Avg Score:74.2%

Providers:1