Model Comparison

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

DeepSeek

DeepSeek-R1-0528

DeepSeek

DeepSeek-R1-0528 is a language model developed by DeepSeek. It achieves strong performance with an average score of 68.1% across 16 benchmarks. It excels particularly in MMLU-Redux (93.4%), AIME 2024 (91.4%), AIME 2025 (87.5%). It supports a 262K token context window for handling large documents. The model is available through 3 API providers. Released in 2025, it represents DeepSeek's latest advancement in AI technology.

Google

Gemini 2.5 Flash-Lite

Google

Gemini 2.5 Flash-Lite is a multimodal language model developed by Google. The model shows competitive results across 13 benchmarks. It excels particularly in FACTS Grounding (84.1%), Global-MMLU-Lite (81.1%), MMMU (72.9%). With a 1.1M token context window, it can handle extensive documents and complex multi-turn conversations. The model is available through 1 API provider. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Google's latest advancement in AI technology.

DeepSeek

DeepSeek-R1-0528

DeepSeek

2025-05-28

Google

Gemini 2.5 Flash-Lite

Google

2025-06-17

20 days newer

Pricing Comparison

Cost per million tokens (USD)

DeepSeek

DeepSeek-R1-0528

Input:$0.50
Output:$2.15
Google

Gemini 2.5 Flash-Lite

$2.15 cheaper
Input:$0.10
Output:$0.40

Performance Metrics

Context window and performance specifications

DeepSeek

DeepSeek-R1-0528

Max Context:262.1K
Parameters:671.0B
Google

Gemini 2.5 Flash-Lite

Larger context
Max Context:1.1M

Average performance across 7 common benchmarks

DeepSeek

DeepSeek-R1-0528

+27.8%
Average Score:59.5%
Google

Gemini 2.5 Flash-Lite

Average Score:31.7%

Performance comparison across key benchmark categories

DeepSeek

DeepSeek-R1-0528

code
+30.8%
73.3%
general
+33.4%
69.2%
Google

Gemini 2.5 Flash-Lite

code
42.5%
general
35.8%
Benchmark Scores - Detailed View
Side-by-side comparison of all benchmark scores
Knowledge Cutoff
Training data recency comparison

Gemini 2.5 Flash-Lite

2025-01-01

More recent knowledge cutoff means awareness of newer technologies and frameworks

Provider Availability & Performance

Available providers and their performance metrics

DeepSeek

DeepSeek-R1-0528

3 providers

DeepInfra

Throughput: 45.04 tok/s
Latency: 0.61ms

Novita

Throughput: 37.96 tok/s
Latency: 1.18ms

DeepSeek

Throughput: 9 tok/s
Latency: 0.3ms
Google

Gemini 2.5 Flash-Lite

1 providers

Google

Throughput: 5.69 tok/s
Latency: 0.44ms
DeepSeek

DeepSeek-R1-0528

+27.8%
Avg Score:59.5%
Providers:3
Google

Gemini 2.5 Flash-Lite

Avg Score:31.7%
Providers:1