Model comparison
Amazon Nova Micro vs Gemini 2.5 Pro
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 30.4 on the Noometry Index. Amazon Nova Micro costs 56× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Gemini 2.5 Pro in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 29.6.
- The biggest single-benchmark swing is LiveBench Coding: 20.2% for Amazon Nova Micro and 85.9% for Gemini 2.5 Pro.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 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 128K.
Side by side
| Amazon Nova Micro | Gemini 2.5 Pro | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 30.4 | 45.0 |
| Released | 2024-12-03 | 2025-03-25 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.035 | $1.25 |
| Output $ / M tokens | $0.14 | $10 |
| Results tracked | 32 | 78 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Amazon Nova Micro: 30.5 (#295), Gemini 2.5 Pro: 42.4 (#101)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| LiveBench Coding | 20.2% | 85.9% |
| LMArena Coding | 1218 | 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 Micro: 22.1 (#132), Gemini 2.5 Pro: 29.2 (#88)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| Terminal-Bench | — | 32.6% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| GDPval | — | 23.3% |
| Remote Labor Index | — | 0.8% |
| TheAgentCompany | — | 30.3% |
| 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 Micro: 17.4 (#294), Gemini 2.5 Pro: 28.8 (#99)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| LiveBench Reasoning | 25.1% | 89.8% |
| LMArena Hard Prompts | 1191 | 1455 |
| LiveBench Data Analysis | 34% | 79.9% |
| LiveBench | 29.6% | 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% |
| Epoch Capabilities Index | — | 145.32 |
| ForecastBench | — | 61.3 |
Math Gemini 2.5 Pro leads
Amazon Nova Micro: 26.9 (#254), Gemini 2.5 Pro: 32.5 (#213)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| Omni-MATH | 21.4% | 41.6% |
| LiveBench Math | 34.5% | 90.2% |
| LMArena Math | 1206 | 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 Micro: 29.6 (#237), Gemini 2.5 Pro: 56.0 (#46)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| MMLU-Pro | 51.1% | 86.3% |
| Vectara Hallucination Rate | 5.5% | 7% |
| GPQA (HELM) | 38.3% | 74.9% |
| LMArena Expert | 1184 | 1452 |
| GPQA Diamond | — | 85.3% |
| Humanity's Last Exam | — | 21.6% |
| Confabulations | — | 10.6% |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Gemini 2.5 Pro: 45.2 (#18)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | — | 1263 |
| GeoBench | — | 86% |
| VPCT | — | 48% |
| LMArena Document | — | 1421 |
| SpatialViz-Bench | — | 44.7% |
Multilingual Gemini 2.5 Pro leads
Amazon Nova Micro: 36.5 (#239), Gemini 2.5 Pro: 55.3 (#31)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1186 | 1451 |
| LMArena Chinese | 1209 | 1507 |
| LMArena French | 1238 | 1472 |
| LMArena German | 1192 | 1487 |
| LMArena Japanese | 1154 | 1461 |
| LMArena Korean | 1150 | 1434 |
| LMArena Russian | 1185 | 1461 |
| LMArena Spanish | 1225 | 1473 |
Instruction Following Gemini 2.5 Pro leads
Amazon Nova Micro: 56.3 (#272), Gemini 2.5 Pro: 75.0 (#75)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| LiveBench Instruction Following | 48% | 80.6% |
| IFEval | 76% | 84% |
| LMArena Instruction Following | 1174 | 1437 |
Long Context Gemini 2.5 Pro leads
Amazon Nova Micro: 36.5 (#229), Gemini 2.5 Pro: 59.8 (#5)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1205 | 1449 |
| Fiction.LiveBench | — | 91.7% |
Writing & Preference Gemini 2.5 Pro leads
Amazon Nova Micro: 39.5 (#247), Gemini 2.5 Pro: 63.7 (#62)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1208 | 1458 |
| LMArena Creative Writing | 1172 | 1454 |
| WildBench | 74.3% | 85.7% |
| LMArena Multi-Turn | 1178 | 1453 |
| LiveBench Language | 15.8% | 67.8% |
| Short-Story Creative Writing | — | 83.8% |
| EQ-Bench Creative Writing | — | 1421 |
Frequently asked questions
Is Amazon Nova Micro better than Gemini 2.5 Pro?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 30.4 on the Noometry Index. Amazon Nova Micro costs 56× 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 Micro or Gemini 2.5 Pro?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Is Amazon Nova Micro or Gemini 2.5 Pro better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 128K.
How many benchmarks do Amazon Nova Micro and Gemini 2.5 Pro share?
30 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Gemini 2.5 Pro has 78.