Amazon Nova Pro
Amazon Nova Pro.
29
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Amazon Dec 2024 Amazon Nova Pro
Closed weights
No Epoch Capabilities Index score yet
- Humanity's Last Exam 4.40% #44 /47
- GPQA Main 44.6% #38 /60
- VISTA 26.3% #49 /54
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 (2025 dataset) | 5.10% | #10 of 104 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 1.80% | #19 of 148 | Official leaderboard | |
| IFEval | 81.5% | #39 of 60 | Official leaderboard | |
| LMArena (Elo) | 1,290 | #234 of 335 | Official leaderboard | |
| SnorkelSpatial | 12.1% | #25 of 27 | Official leaderboard | |
| LLM Confabulation Leaderboard | 30.1% | #54 of 58 | Official leaderboard | |
| Humanity's Last Exam | 4.40% | #44 of 47 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Main | 44.6% | #38 of 60 | Official leaderboard | |
| SnorkelSequences | 41.2% | #18 of 25 | Official leaderboard | |
| SnorkelGraph | 28% | #18 of 24 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DesignArena Website | 789 | #149 of 151 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) | 60.8% | #23 of 67 | Official leaderboard | |
| Galileo Agent Leaderboard | 0.87 | #15 of 29 | Official leaderboard | |
| Elimination Game | 4 | #37 of 56 | Official leaderboard | |
| LisanBench | 146.0 | #100 of 133 | Official leaderboard | |
| BFCL V4 | 25% | #52 of 65 | Official leaderboard | |
| Galileo Agent Leaderboard v2 | 29% | #17 of 21 | Official leaderboard | |
| ToolComp | 47% | #26 of 32 | Official leaderboard | |
| PACT | 1,426 | #25 of 26 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MedQA | 81.1% | #6 of 71 | Official leaderboard | |
| SnorkelUnderwrite | 52.3% | #16 of 27 | Official leaderboard | |
| FinQA (Snorkel OpenEnv environment) | 40.3% | #20 of 22 | Official leaderboard | |
| SnorkelFinance | 40.3% | #20 of 22 | Official leaderboard | |
| Finance Reasoning (Snorkel) | 12.7% | #21 of 21 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMU | 62% | #53 of 136 | Official leaderboard | |
| VISTA | 26.3% | #49 of 54 | Official leaderboard | |
| Vision Arena | 1,019 | #126 of 136 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Lite | 88.5 | #5 of 71 | Official leaderboard | |
| HELM Capabilities | 59.1 | #45 of 60 | Official leaderboard |