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 72B Instruct

Alibaba

Qwen2 72B Instruct is a language model developed by Alibaba. It achieves strong performance with an average score of 73.6% across 17 benchmarks. It excels particularly in GSM8k (91.1%), CMMLU (90.1%), HellaSwag (87.6%). The model shows particular specialization in code tasks with an average performance of 82.3%. Released in 2024, it represents Alibaba's latest advancement in AI technology.

Alibaba

Qwen2 72B Instruct

Alibaba

2024-07-23

Amazon

Nova Micro

Amazon

2024-11-20

4 months newer

Performance Metrics

Context window and performance specifications

Amazon

Nova Micro

Larger context
Max Context:256.0K
Alibaba

Qwen2 72B Instruct

Max Context:-
Parameters:72.0B

Average performance across 7 common benchmarks

Amazon

Nova Micro

+2.5%
Average Score:75.7%
Alibaba

Qwen2 72B Instruct

Average Score:73.3%

Performance comparison across key benchmark categories

Amazon

Nova Micro

reasoning
+9.7%
90.2%
code
+1.9%
84.2%
math
+5.4%
80.8%
general
60.0%
Alibaba

Qwen2 72B Instruct

reasoning
80.5%
code
82.3%
math
75.4%
general
+7.9%
67.9%
Benchmark Scores - Detailed View
Side-by-side comparison of all benchmark scores

Provider Availability & Performance

Available providers and their performance metrics

Amazon

Nova Micro

1 providers

Bedrock

Throughput: 100 tok/s
Latency: 0.5ms
Alibaba

Qwen2 72B Instruct

0 providers
Amazon

Nova Micro

+2.5%
Avg Score:75.7%
Providers:1
Alibaba

Qwen2 72B Instruct

Avg Score:73.3%
Providers:0