Model comparison
Amazon Nova Pro vs Gemini 3 Pro
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 31.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Gemini 3 Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Pro leads 64.4 to 27.4.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 72.5% for Gemini 3 Pro.
Side by side
| Amazon Nova Pro | Gemini 3 Pro | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 31.0 | 54.8 |
| Released | 2024-12-03 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Amazon Nova Pro: 35.1 (#229), Gemini 3 Pro: 51.6 (#39)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| LMArena Coding | 1270 | 1481 |
| SWE-bench Verified | — | 72.9% |
| SWE-bench Verified (bash only) | — | 74.2% |
| LMArena WebDev | — | 1440 |
| SWE-bench Multilingual | — | 68.7% |
| GSO | — | 18.6% |
| WeirdML | — | 69.9% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,177 |
| AlgoTune | — | 1.83 |
Agentic & Tool Use Gemini 3 Pro leads
Amazon Nova Pro: 16.7 (#147), Gemini 3 Pro: 40.6 (#23)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 72.5% |
| Terminal-Bench | — | 69.4% |
| GDPval | — | 40.3% |
| Remote Labor Index | — | 1.3% |
| TheAgentCompany | 1.7% | — |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Banking | — | 18% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| DeepResearch Bench | — | 46.3% |
| BALROG | — | 58.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 71% |
| Vending-Bench 2 | — | 5,478 |
Reasoning Gemini 3 Pro leads
Amazon Nova Pro: 20.0 (#243), Gemini 3 Pro: 52.5 (#31)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1480 |
| Epoch Capabilities Index | 123.8 | 152.92 |
| ARC-AGI-2 | — | 31.1% |
| SimpleBench | — | 76.4% |
| Kagi LLM Benchmark | — | 80.1% |
| NYT Connections (extended) | — | 94.4% |
| ARC-AGI-1 | — | 75% |
| CritPt | — | 6.9% |
| Chess Puzzles | — | 31% |
| EnigmaEval | — | 18.2% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| ForecastBench | — | 61.2 |
| LiveBench | 43.5% | — |
Math Gemini 3 Pro leads
Amazon Nova Pro: 28.5 (#243), Gemini 3 Pro: 49.9 (#59)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| Omni-MATH | 24.2% | 55.5% |
| LMArena Math | 1252 | 1476 |
| MathArena Final-Answer Competitions | — | 67% |
| OTIS Mock AIME 2024-2025 | — | 91.4% |
| ProofBench | — | 20% |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 37.6% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge Gemini 3 Pro leads
Amazon Nova Pro: 27.4 (#250), Gemini 3 Pro: 64.4 (#16)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| Humanity's Last Exam | 4.4% | 37.5% |
| MMLU-Pro | 67.3% | 90.3% |
| Vectara Hallucination Rate | 5.1% | 13.6% |
| GPQA (HELM) | 44.6% | 80.3% |
| LMArena Expert | 1211 | 1475 |
| GPQA Diamond | — | 92.6% |
| Confabulations | 30.1% | — |
| MMLU | 82% | — |
Multimodal Gemini 3 Pro leads
Amazon Nova Pro: 25.0 (#126), Gemini 3 Pro: 57.6 (#2)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 980 | 1305 |
| GeoBench | — | 84% |
| VPCT | — | 91% |
| LMArena Document | — | 1434 |
Multilingual Gemini 3 Pro leads
Amazon Nova Pro: 39.7 (#223), Gemini 3 Pro: 56.9 (#16)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1234 | 1474 |
| LMArena Chinese | 1244 | 1523 |
| LMArena French | 1271 | 1492 |
| LMArena German | 1243 | 1515 |
| LMArena Japanese | 1200 | 1510 |
| LMArena Korean | 1203 | 1448 |
| LMArena Russian | 1240 | 1493 |
| LMArena Spanish | 1182 | 1470 |
Instruction Following Gemini 3 Pro leads
Amazon Nova Pro: 64.9 (#226), Gemini 3 Pro: 76.3 (#45)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| IFEval | 81.5% | 87.7% |
| LMArena Instruction Following | 1235 | 1458 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Gemini 3 Pro leads
Amazon Nova Pro: 38.1 (#205), Gemini 3 Pro: 44.0 (#79)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1255 | 1471 |
| CL-bench | — | 15.8% |
Writing & Preference Gemini 3 Pro leads
Amazon Nova Pro: 43.9 (#226), Gemini 3 Pro: 66.4 (#35)
| Benchmark | Amazon Nova Pro | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1259 | 1479 |
| LMArena Creative Writing | 1212 | 1482 |
| WildBench | 77.7% | 85.9% |
| LMArena Multi-Turn | 1246 | 1484 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1525 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Gemini 3 Pro?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 31.0 on the Noometry Index.
Is Amazon Nova Pro or Gemini 3 Pro better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 35.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Gemini 3 Pro share?
27 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemini 3 Pro has 67.