Amazon Nova Micro
Amazon Nova Micro.
21
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| 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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| 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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| 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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| 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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Lite | 52.4 | #35 of 71 | Official leaderboard | |
| HELM Capabilities | 52.2 | #53 of 60 | Official leaderboard |