Model Comparison

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

Amazon

Nova Micro

Amazon

Nova Micro is a language model developed by Amazon. It achieves strong performance with an average score of 67.0% across 17 benchmarks. It excels particularly in GSM8k (92.3%), ARC-C (90.2%), Translation Set1→en COMET22 (88.7%). It supports a 256K token context window for handling large documents. The model is available through 1 API provider. Released in 2024, it represents Amazon's latest advancement in AI technology.

Alibaba

Qwen2.5 VL 72B Instruct

Alibaba

Qwen2.5 VL 72B Instruct is a multimodal language model developed by Alibaba. It achieves strong performance with an average score of 66.9% across 30 benchmarks. It excels particularly in DocVQA (96.4%), Android Control Low_EM (93.7%), ChartQA (89.5%). As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Alibaba's latest advancement in AI technology.

Amazon

Nova Micro

Amazon

2024-11-20

Alibaba

Qwen2.5 VL 72B Instruct

Alibaba

2025-01-26

2 months newer

Performance Metrics

Context window and performance specifications

Amazon

Nova Micro

Larger context
Max Context:256.0K
Alibaba

Qwen2.5 VL 72B Instruct

Max Context:-
Parameters:72.0B

Performance comparison across key benchmark categories

Amazon

Nova Micro

math
+24.4%
80.8%
general
60.0%
Alibaba

Qwen2.5 VL 72B Instruct

math
56.5%
general
+9.6%
69.6%

Provider Availability & Performance

Available providers and their performance metrics

Amazon

Nova Micro

1 providers

Bedrock

Throughput: 100 tok/s
Latency: 0.5ms
Alibaba

Qwen2.5 VL 72B Instruct

0 providers
Amazon

Nova Micro

Avg Score:0.0%
Providers:1
Alibaba

Qwen2.5 VL 72B Instruct

Avg Score:0.0%
Providers:0