Noometry

Model comparison

Amazon Nova Micro vs Tulu 3 (Tülu 3) 70B

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 29.9 on the Noometry Index.

Last verified . 11 shared benchmarks.

Amazon Nova Micro Amazon

29.9

Rank #290 Confirmed

Tulu 3 (Tülu 3) 70B Allen Institute for AI (Ai2)

32.6

Rank #242 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Amazon Nova Micro scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Amazon Nova Micro leads 24.9 to 13.3.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroTulu 3 (Tülu 3) 70B
ProviderAmazonAllen Institute for AI (Ai2)
Noometry Index29.932.6
Released2024-12-032024-11-21
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3214

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

Category by category

Coding Tulu 3 (Tülu 3) 70B leads

Amazon Nova Micro: 30.0 (#289), Tulu 3 (Tülu 3) 70B: 35.4 (#211)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
LMArena Coding12181236
LiveBench Coding20.2%—

Agentic & Tool Use Not comparable

Amazon Nova Micro: 21.9 (#125), Tulu 3 (Tülu 3) 70B: —

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
Berkeley Function Calling Leaderboard22.3%—

Reasoning Tulu 3 (Tülu 3) 70B leads

Amazon Nova Micro: 16.7 (#289), Tulu 3 (Tülu 3) 70B: 22.9 (#172)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
LMArena Hard Prompts11911220
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—

Math Amazon Nova Micro leads

Amazon Nova Micro: 24.9 (#252), Tulu 3 (Tülu 3) 70B: 13.3 (#297)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
LMArena Math12061242
OTIS Mock AIME 2024-2025—4.4%
Omni-MATH21.4%—
LiveBench Math34.5%—
MATH Level 5—42.7%

Knowledge Amazon Nova Micro leads

Amazon Nova Micro: 29.2 (#231), Tulu 3 (Tülu 3) 70B: 25.1 (#257)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
GPQA Diamond—46.3%
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
LMArena Expert1184—
MMLU70.8%—

Multilingual Tulu 3 (Tülu 3) 70B leads

Amazon Nova Micro: 36.7 (#234), Tulu 3 (Tülu 3) 70B: 40.1 (#217)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
LMArena Non-English11861236
LMArena Chinese12091249
LMArena Russian11851246
LMArena French1237—
LMArena German1192—
LMArena Japanese1154—
LMArena Korean1150—
LMArena Spanish1225—

Instruction Following Tulu 3 (Tülu 3) 70B leads

Amazon Nova Micro: 56.6 (#267), Tulu 3 (Tülu 3) 70B: 65.0 (#222)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
LMArena Instruction Following11741233
LiveBench Instruction Following48%—
IFEval76%—

Long Context Too close to call

Amazon Nova Micro: 36.5 (#224), Tulu 3 (Tülu 3) 70B: 37.1 (#217)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
LMArena Longer Query12061224

Writing & Preference Tulu 3 (Tülu 3) 70B leads

Amazon Nova Micro: 39.7 (#242), Tulu 3 (Tülu 3) 70B: 45.8 (#218)

BenchmarkAmazon Nova MicroTulu 3 (Tülu 3) 70B
LMArena Text12081256
LMArena Creative Writing11721231
LMArena Multi-Turn11781252
WildBench74.3%—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Tulu 3 (Tülu 3) 70B?

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 32.6 to 29.9 on the Noometry Index.

Is Amazon Nova Micro or Tulu 3 (Tülu 3) 70B better for coding?

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 35.4 versus 30.0 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and Tulu 3 (Tülu 3) 70B share?

11 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper