Model comparison
Amazon Nova Micro vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 30.4 on the Noometry Index. Amazon Nova Micro costs 14× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Gemini 2.5 Flash in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemini 2.5 Flash leads 75.7 to 56.3.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 22.3% for Amazon Nova Micro and 56.2% for Gemini 2.5 Flash.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 128K.
Side by side
| Amazon Nova Micro | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 30.4 | 39.3 |
| Released | 2024-12-03 | 2025-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.035 | $0.30 |
| Output $ / M tokens | $0.14 | $2.50 |
| Results tracked | 32 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Amazon Nova Micro: 30.5 (#295), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Coding | 1218 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| WeirdML | — | 41.9% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 661.88 |
Agentic & Tool Use Gemini 2.5 Flash leads
Amazon Nova Micro: 22.1 (#132), Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 56.2% |
| Terminal-Bench | — | 17.1% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |
Reasoning Too close to call
Amazon Nova Micro: 17.4 (#294), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1422 |
| 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 | 25.1% | — |
| DTBench | — | 76.5% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 27.5% |
| Epoch Capabilities Index | — | 143.03 |
| ForecastBench | — | 60.6 |
| LiveBench | 29.6% | — |
Math Gemini 2.5 Flash leads
Amazon Nova Micro: 26.9 (#254), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| Omni-MATH | 21.4% | 38.5% |
| LMArena Math | 1206 | 1415 |
| OTIS Mock AIME 2024-2025 | — | 73.1% |
| LiveBench Math | 34.5% | — |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Flash leads
Amazon Nova Micro: 29.6 (#237), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| MMLU-Pro | 51.1% | 63.9% |
| Vectara Hallucination Rate | 5.5% | 7.8% |
| GPQA (HELM) | 38.3% | 39% |
| LMArena Expert | 1184 | 1426 |
| Humanity's Last Exam | — | 12.1% |
| Confabulations | — | 16.8% |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Amazon Nova Micro: 36.5 (#239), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1186 | 1409 |
| LMArena Chinese | 1209 | 1450 |
| LMArena French | 1238 | 1433 |
| LMArena German | 1192 | 1418 |
| LMArena Japanese | 1154 | 1405 |
| LMArena Korean | 1150 | 1385 |
| LMArena Russian | 1185 | 1415 |
| LMArena Spanish | 1225 | 1421 |
Instruction Following Gemini 2.5 Flash leads
Amazon Nova Micro: 56.3 (#272), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| IFEval | 76% | 89.8% |
| LMArena Instruction Following | 1174 | 1405 |
| LiveBench Instruction Following | 48% | — |
Long Context Gemini 2.5 Flash leads
Amazon Nova Micro: 36.5 (#229), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1205 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 2.5 Flash leads
Amazon Nova Micro: 39.5 (#247), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Amazon Nova Micro | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1208 | 1417 |
| LMArena Creative Writing | 1172 | 1400 |
| WildBench | 74.3% | 81.7% |
| LMArena Multi-Turn | 1178 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| EQ-Bench Creative Writing | — | 1137 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 30.4 on the Noometry Index. Amazon Nova Micro costs 14× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Gemini 2.5 Flash?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Amazon Nova Micro or Gemini 2.5 Flash better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 128K.
How many benchmarks do Amazon Nova Micro and Gemini 2.5 Flash share?
24 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Gemini 2.5 Flash has 54.