Benchmark Almanac

Amazon Nova Micro

Amazon Nova Micro.

Amazon Released December 3rd, 2024 Compare with others
21
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Amazon Dec 2024

Amazon Nova Micro

Closed weights

No Epoch Capabilities Index score yet
  • GPQA Main 38.3% #48 /60
  • ToolComp 28.9% #31 /32
  • SnorkelSequences 33.6% #25 /25

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
Vectara Hallucination Leaderboard (HHEM) 1.60% #14 of 148 Official leaderboard
Vectara Hallucination Leaderboard (2025 dataset) 5.50% #18 of 104 Official leaderboard
SnorkelSpatial 14.6% #17 of 27 Official leaderboard
CulturalRiddles 8.30% #14 of 20 Official leaderboard
LMArena (Elo) 1,241 #265 of 335 Official leaderboard
IFEval 76% #52 of 60 Official leaderboard

Math and science

BenchmarkScoreRankSource
GPQA Main 38.3% #48 of 60 Official leaderboard
SnorkelGraph 17.5% #23 of 24 Official leaderboard
SnorkelSequences 33.6% #25 of 25 Official leaderboard

Agents and tools

BenchmarkScoreRankSource
Galileo Agent Leaderboard 0.83 #19 of 29 Official leaderboard
Berkeley Function Calling Leaderboard (BFCL) 51.8% #45 of 67 Official leaderboard
BFCL V4 22.3% #56 of 65 Official leaderboard
MCP-Bench 0.51 #13 of 15 Official leaderboard
LisanBench 76.0 #117 of 133 Official leaderboard
ToolComp 28.9% #31 of 32 Official leaderboard

Professional work

BenchmarkScoreRankSource
MedQA 60.8% #50 of 71 Official leaderboard
SnorkelUnderwrite 31% #23 of 27 Official leaderboard
FinQA (Snorkel OpenEnv environment) 14.5% #22 of 22 Official leaderboard
SnorkelFinance 14.5% #22 of 22 Official leaderboard

Other

BenchmarkScoreRankSource
HELM Lite 52.4 #35 of 71 Official leaderboard
HELM Capabilities 52.2 #53 of 60 Official leaderboard