Noometry

Model comparison

Amazon Nova Micro vs Qwen2.5 7B Instruct

Amazon Nova Micro is the stronger model overall, scoring 29.9 to 28.6 on the Noometry Index.

Last verified . 6 shared benchmarks.

Amazon Nova Micro Amazon

29.9

Rank #290 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

28.6

Rank #314 Confirmed

Summary

  • They share 6 benchmarks with published results for both. Amazon Nova Micro scores higher in 3 categories and Qwen2.5 7B Instruct in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Amazon Nova Micro leads 24.9 to 11.8.
  • The biggest single-benchmark swing is Omni-MATH: 21.4% for Amazon Nova Micro and 29.4% for Qwen2.5 7B Instruct.
  • Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
  • Qwen2.5 7B Instruct accepts more context: 131K tokens versus 128K.
  • Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroQwen2.5 7B Instruct
ProviderAmazonAlibaba (Qwen)
Noometry Index29.928.6
Released2024-12-032024-09
WeightsProprietaryOpen
Context window128K131K
Max output10K8K
Input $ / M tokens$0.035$0.17
Output $ / M tokens$0.14$0.70
Results tracked3215

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen2.5 7B Instruct leads

Amazon Nova Micro: 30.0 (#289), Qwen2.5 7B Instruct: 35.9 (#204)

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
BigCodeBench Instruct—37.6%
LiveBench Coding20.2%—
LMArena Coding1218—
BigCodeBench Complete—46.1%

Agentic & Tool Use Qwen2.5 7B Instruct leads

Amazon Nova Micro: 21.9 (#125), Qwen2.5 7B Instruct: 23.5 (#117)

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
Berkeley Function Calling Leaderboard22.3%—
BALROG—7.8%

Reasoning Amazon Nova Micro leads

Amazon Nova Micro: 16.7 (#289), Qwen2.5 7B Instruct: 14.3 (#317)

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
Chess Puzzles—0%
LiveBench Reasoning25.1%—
LMArena Hard Prompts1191—
DTBench—47.7%
LiveBench Data Analysis34%—
LMCA—6.4%
Epoch Capabilities Index—118.44
LiveBench29.6%—

Math Amazon Nova Micro leads

Amazon Nova Micro: 24.9 (#252), Qwen2.5 7B Instruct: 11.8 (#300)

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
Omni-MATH21.4%29.4%
OTIS Mock AIME 2024-2025—2.5%
LiveBench Math34.5%—
LMArena Math1206—

Knowledge Amazon Nova Micro leads

Amazon Nova Micro: 29.2 (#231), Qwen2.5 7B Instruct: 17.0 (#281)

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
MMLU-Pro51.1%53.9%
GPQA (HELM)38.3%34.1%
MMLU70.8%72.9%
GPQA Diamond—35.5%
Vectara Hallucination Rate5.5%—
LMArena Expert1184—

Multilingual Not comparable

Amazon Nova Micro: 36.7 (#234), Qwen2.5 7B Instruct: —

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
LMArena Non-English1186—
LMArena Chinese1209—
LMArena French1237—
LMArena German1192—
LMArena Japanese1154—
LMArena Korean1150—
LMArena Russian1185—
LMArena Spanish1225—

Instruction Following Qwen2.5 7B Instruct leads

Amazon Nova Micro: 56.6 (#267), Qwen2.5 7B Instruct: 63.4 (#226)

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
IFEval76%74.1%
LiveBench Instruction Following48%—
LMArena Instruction Following1174—

Long Context Not comparable

Amazon Nova Micro: 36.5 (#224), Qwen2.5 7B Instruct: —

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
LMArena Longer Query1206—

Writing & Preference Qwen2.5 7B Instruct leads

Amazon Nova Micro: 39.7 (#242), Qwen2.5 7B Instruct: 48.8 (#194)

BenchmarkAmazon Nova MicroQwen2.5 7B Instruct
WildBench74.3%73.1%
LMArena Text1208—
LMArena Creative Writing1172—
LMArena Multi-Turn1178—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Qwen2.5 7B Instruct?

Amazon Nova Micro is the stronger model overall, scoring 29.9 to 28.6 on the Noometry Index.

Which is cheaper, Amazon Nova Micro or Qwen2.5 7B Instruct?

Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.

Is Amazon Nova Micro or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 30.0 in the Noometry coding category.

Which has the bigger context window?

Qwen2.5 7B Instruct does, with 131K tokens against 128K.

How many benchmarks do Amazon Nova Micro and Qwen2.5 7B Instruct share?

6 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper