Model comparison
Amazon Nova Pro vs Gemini 2.5 Pro
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.5× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
GoogleSummary
- They share 36 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Gemini 2.5 Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 27.4.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.6% for Amazon Nova Pro and 89.8% for Gemini 2.5 Pro.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Pro | Gemini 2.5 Pro | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 31.0 | 45.0 |
| Released | 2024-12-03 | 2025-03-25 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.80 | $1.25 |
| Output $ / M tokens | $3.20 | $10 |
| Results tracked | 38 | 78 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Amazon Nova Pro: 35.1 (#229), Gemini 2.5 Pro: 42.4 (#101)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| LiveBench Coding | 38.1% | 85.9% |
| LMArena Coding | 1270 | 1452 |
| SWE-bench Verified | — | 57.6% |
| SWE-bench Verified (bash only) | — | 53.6% |
| Aider Polyglot | — | 83.1% |
| LMArena WebDev | — | 1227 |
| SciCode | — | 42.8% |
| GSO | — | 3.9% |
| WeirdML | — | 54% |
| CadEval | — | 64% |
| ALE-Bench | — | 785.52 |
| AlgoTune | — | 1.51 |
Agentic & Tool Use Gemini 2.5 Pro leads
Amazon Nova Pro: 16.7 (#147), Gemini 2.5 Pro: 29.2 (#88)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| TheAgentCompany | 1.7% | 30.3% |
| Terminal-Bench | — | 32.6% |
| Berkeley Function Calling Leaderboard | 25% | — |
| GDPval | — | 23.3% |
| Remote Labor Index | — | 0.8% |
| τ²-bench Banking | — | 13.7% |
| DeepResearch Bench | — | 42.8% |
| BALROG | — | 43.3% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 55.4% |
| Vending-Bench 2 | — | 573.64 |
Reasoning Gemini 2.5 Pro leads
Amazon Nova Pro: 20.0 (#243), Gemini 2.5 Pro: 28.8 (#99)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| LiveBench Reasoning | 32.6% | 89.8% |
| LMArena Hard Prompts | 1246 | 1455 |
| LiveBench Data Analysis | 48.3% | 79.9% |
| Epoch Capabilities Index | 123.8 | 145.32 |
| LiveBench | 43.5% | 82.3% |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 62.4% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 41% |
| CritPt | — | 2% |
| Chess Puzzles | — | 20% |
| EnigmaEval | — | 5.6% |
| DTBench | — | 82.4% |
| LMCA | — | 34.8% |
| ForecastBench | — | 61.3 |
Math Gemini 2.5 Pro leads
Amazon Nova Pro: 28.5 (#243), Gemini 2.5 Pro: 32.5 (#213)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| Omni-MATH | 24.2% | 41.6% |
| LiveBench Math | 38% | 90.2% |
| LMArena Math | 1252 | 1450 |
| FrontierMath (Tiers 1-3) | — | 24.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 84.7% |
| MATH Level 5 | — | 95.9% |
| FrontierMath (Feb 2025 set) | — | 14.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Pro leads
Amazon Nova Pro: 27.4 (#250), Gemini 2.5 Pro: 56.0 (#46)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| Humanity's Last Exam | 4.4% | 21.6% |
| MMLU-Pro | 67.3% | 86.3% |
| Confabulations | 30.1% | 10.6% |
| Vectara Hallucination Rate | 5.1% | 7% |
| GPQA (HELM) | 44.6% | 74.9% |
| LMArena Expert | 1211 | 1452 |
| GPQA Diamond | — | 85.3% |
| MMLU | 82% | — |
Multimodal Gemini 2.5 Pro leads
Amazon Nova Pro: 25.0 (#126), Gemini 2.5 Pro: 45.2 (#18)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | 980 | 1263 |
| GeoBench | — | 86% |
| VPCT | — | 48% |
| LMArena Document | — | 1421 |
| SpatialViz-Bench | — | 44.7% |
Multilingual Gemini 2.5 Pro leads
Amazon Nova Pro: 39.7 (#223), Gemini 2.5 Pro: 55.3 (#31)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1234 | 1451 |
| LMArena Chinese | 1244 | 1507 |
| LMArena French | 1271 | 1472 |
| LMArena German | 1243 | 1487 |
| LMArena Japanese | 1200 | 1461 |
| LMArena Korean | 1203 | 1434 |
| LMArena Russian | 1240 | 1461 |
| LMArena Spanish | 1182 | 1473 |
Instruction Following Gemini 2.5 Pro leads
Amazon Nova Pro: 64.9 (#226), Gemini 2.5 Pro: 75.0 (#75)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 80.6% |
| IFEval | 81.5% | 84% |
| LMArena Instruction Following | 1235 | 1437 |
Long Context Gemini 2.5 Pro leads
Amazon Nova Pro: 38.1 (#205), Gemini 2.5 Pro: 59.8 (#5)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1255 | 1449 |
| Fiction.LiveBench | — | 91.7% |
Writing & Preference Gemini 2.5 Pro leads
Amazon Nova Pro: 43.9 (#226), Gemini 2.5 Pro: 63.7 (#62)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1259 | 1458 |
| LMArena Creative Writing | 1212 | 1454 |
| Short-Story Creative Writing | 60.5% | 83.8% |
| WildBench | 77.7% | 85.7% |
| LMArena Multi-Turn | 1246 | 1453 |
| LiveBench Language | 37% | 67.8% |
| EQ-Bench Creative Writing | — | 1421 |
Frequently asked questions
Is Amazon Nova Pro better than Gemini 2.5 Pro?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.5× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Gemini 2.5 Pro?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Is Amazon Nova Pro or Gemini 2.5 Pro better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and Gemini 2.5 Pro share?
36 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemini 2.5 Pro has 78.