Amazon

Nova Micro

Zero-eval
#3Translation Set1→en COMET22
#3Translation en→Set1 COMET22
#3FinQA
+3 more

by Amazon

About

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.

Pricing Range
Input (per 1M)$0.03 -$0.03
Output (per 1M)$0.14 -$0.14
Providers1
Timeline
AnnouncedNov 20, 2024
ReleasedNov 20, 2024
Specifications
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown

Overall Performance

17 benchmarks
Average Score
67.0%
Best Score
92.3%
High Performers (80%+)
6

Performance Metrics

Max Context Window
256.0K
Avg Throughput
100.0 tok/s
Avg Latency
1ms

Top Categories

reasoning
90.2%
code
84.2%
math
80.8%
general
60.0%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark

GSM8k

Rank #19 of 46
#16Claude 3 Sonnet
92.3%
#17Mistral Large 2
93.0%
#18Qwen3 235B A22B
94.4%
#19Nova Micro
92.3%
#20Kimi K2 Base
92.1%
#21Qwen2.5 7B Instruct
91.6%
#22Llama 3.1 Nemotron 70B Instruct
91.4%

ARC-C

Rank #10 of 31
#7Phi-3.5-MoE-instruct
91.0%
#8Mistral Small 3 24B Base
91.3%
#9Nova Lite
92.4%
#10Nova Micro
90.2%
#11Claude 3 Haiku
89.2%
#12Jamba 1.5 Mini
85.7%
#13Phi-3.5-mini-instruct
84.6%

Translation Set1→en COMET22

Rank #3 of 3
#1Nova Lite
88.8%
#2Nova Pro
89.0%
#3Nova Micro
88.7%

Translation en→Set1 COMET22

Rank #3 of 3
#1Nova Lite
88.8%
#2Nova Pro
89.1%
#3Nova Micro
88.5%

IFEval

Rank #17 of 37
#14Kimi-k1.5
87.2%
#15GPT-4.1
87.4%
#16Llama 3.1 70B Instruct
87.5%
#17Nova Micro
87.2%
#18DeepSeek-V3
86.1%
#19Phi 4 Reasoning Plus
84.9%
#20Qwen2.5 72B Instruct
84.1%
All Benchmark Results for Nova Micro
Complete list of benchmark scores with detailed information
GSM8k
GSM8k benchmark
math
text
0.92
92.3%
Self-reported
ARC-C
ARC-C benchmark
reasoning
text
0.90
90.2%
Self-reported
Translation Set1→en COMET22
Translation Set1→en COMET22 benchmark
general
text
0.89
88.7%
Self-reported
Translation en→Set1 COMET22
Translation en→Set1 COMET22 benchmark
general
text
0.89
88.5%
Self-reported
IFEval
IFEval benchmark
code
text
0.87
87.2%
Self-reported
HumanEval
HumanEval benchmark
code
text
0.81
81.1%
Self-reported
BBH
BBH benchmark
general
text
0.80
79.5%
Self-reported
DROP
DROP benchmark
general
text
0.79
79.3%
Self-reported
MMLU
MMLU benchmark
general
text
0.78
77.6%
Self-reported
MATH
MATH benchmark
math
text
0.69
69.3%
Self-reported
Showing 1 to 10 of 17 benchmarks