Model Comparison

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

DeepSeek

DeepSeek R1 Distill Qwen 1.5B

DeepSeek

DeepSeek R1 Distill Qwen 1.5B is a language model developed by DeepSeek. The model shows competitive results across 4 benchmarks. It excels particularly in MATH-500 (83.9%), AIME 2024 (52.7%), GPQA (33.8%). 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

DeepSeek-V2.5

DeepSeek

DeepSeek-V2.5 is a language model developed by DeepSeek. It achieves strong performance with an average score of 71.1% across 15 benchmarks. It excels particularly in GSM8k (95.1%), MT-Bench (90.2%), HumanEval (89.0%). The model is available through 3 API providers. Released in 2024, it represents DeepSeek's latest advancement in AI technology.

DeepSeek

DeepSeek-V2.5

DeepSeek

2024-05-08

DeepSeek

DeepSeek R1 Distill Qwen 1.5B

DeepSeek

2025-01-20

8 months newer

Performance Metrics

Context window and performance specifications

DeepSeek

DeepSeek R1 Distill Qwen 1.5B

Max Context:-
Parameters:1.8B
DeepSeek

DeepSeek-V2.5

Larger context
Max Context:16.4K
Parameters:236.0B

Performance comparison across key benchmark categories

DeepSeek

DeepSeek R1 Distill Qwen 1.5B

math
83.9%
general
43.3%
code
16.9%
DeepSeek

DeepSeek-V2.5

math
+1.0%
84.9%
general
+25.1%
68.4%
code
+49.2%
66.1%

Provider Availability & Performance

Available providers and their performance metrics

DeepSeek

DeepSeek R1 Distill Qwen 1.5B

0 providers
DeepSeek

DeepSeek-V2.5

3 providers

Hyperbolic

Throughput: 100 tok/s
Latency: 0.5ms

DeepInfra

Throughput: 63 tok/s
Latency: 0.5ms

DeepSeek

Throughput: 100 tok/s
Latency: 0.5ms
DeepSeek

DeepSeek R1 Distill Qwen 1.5B

Avg Score:0.0%
Providers:0
DeepSeek

DeepSeek-V2.5

Avg Score:0.0%
Providers:3