Model comparison
Amazon Nova Pro vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 31.0 on the Noometry Index.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Gemini 2.5 Flash in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 2.5 Flash leads 41.8 to 25.0.
- The biggest single-benchmark swing is TheAgentCompany: 1.7% for Amazon Nova Pro and 41.1% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Pro | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 31.0 | 39.3 |
| Released | 2024-12-03 | 2025-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.80 | $0.30 |
| Output $ / M tokens | $3.20 | $2.50 |
| Results tracked | 38 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Pro: 35.1 (#229), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Coding | 1270 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| WeirdML | — | 41.9% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 661.88 |
Agentic & Tool Use Gemini 2.5 Flash leads
Amazon Nova Pro: 16.7 (#147), Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 56.2% |
| TheAgentCompany | 1.7% | 41.1% |
| Terminal-Bench | — | 17.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1422 |
| Epoch Capabilities Index | 123.8 | 143.03 |
| ARC-AGI-2 | — | 2.5% |
| SimpleBench | — | 41.2% |
| Kagi LLM Benchmark | — | 56.8% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| EnigmaEval | — | 2.7% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 76.5% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 27.5% |
| ForecastBench | — | 60.6 |
| LiveBench | 43.5% | — |
Math Gemini 2.5 Flash leads
Amazon Nova Pro: 28.5 (#243), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| Omni-MATH | 24.2% | 38.5% |
| LMArena Math | 1252 | 1415 |
| OTIS Mock AIME 2024-2025 | — | 73.1% |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Flash leads
Amazon Nova Pro: 27.4 (#250), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| Humanity's Last Exam | 4.4% | 12.1% |
| MMLU-Pro | 67.3% | 63.9% |
| Confabulations | 30.1% | 16.8% |
| Vectara Hallucination Rate | 5.1% | 7.8% |
| GPQA (HELM) | 44.6% | 39% |
| LMArena Expert | 1211 | 1426 |
| MMLU | 82% | — |
Multimodal Gemini 2.5 Flash leads
Amazon Nova Pro: 25.0 (#126), Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | 980 | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Amazon Nova Pro: 39.7 (#223), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1234 | 1409 |
| LMArena Chinese | 1244 | 1450 |
| LMArena French | 1271 | 1433 |
| LMArena German | 1243 | 1418 |
| LMArena Japanese | 1200 | 1405 |
| LMArena Korean | 1203 | 1385 |
| LMArena Russian | 1240 | 1415 |
| LMArena Spanish | 1182 | 1421 |
Instruction Following Gemini 2.5 Flash leads
Amazon Nova Pro: 64.9 (#226), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| IFEval | 81.5% | 89.8% |
| LMArena Instruction Following | 1235 | 1405 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Gemini 2.5 Flash leads
Amazon Nova Pro: 38.1 (#205), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1255 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 2.5 Flash leads
Amazon Nova Pro: 43.9 (#226), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Amazon Nova Pro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1259 | 1417 |
| LMArena Creative Writing | 1212 | 1400 |
| Short-Story Creative Writing | 60.5% | 76.5% |
| WildBench | 77.7% | 81.7% |
| LMArena Multi-Turn | 1246 | 1408 |
| EQ-Bench Creative Writing | — | 1137 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Gemini 2.5 Flash?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Gemini 2.5 Flash better for coding?
They score almost the same on coding (35.1 vs 35.8); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and Gemini 2.5 Flash share?
30 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemini 2.5 Flash has 54.