Model comparison
Amazon Nova Micro vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 30.4 on the Noometry Index. Amazon Nova Micro costs 6.1× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 39.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 12.3% for Mercury 2.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
Side by side
| Amazon Nova Micro | Mercury 2 | |
|---|---|---|
| Provider | Amazon | Inception |
| Noometry Index | 30.4 | 39.1 |
| Released | 2024-12-03 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 128K |
| Max output | 10K | 50K |
| Input $ / M tokens | $0.035 | $0.25 |
| Output $ / M tokens | $0.14 | $0.75 |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Amazon Nova Micro: 30.5 (#295), Mercury 2: 33.5 (#255)
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| LMArena Coding | 1218 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 785.58 |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 22.1 (#132), Mercury 2: —
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Mercury 2 leads
Amazon Nova Micro: 17.4 (#294), Mercury 2: 23.8 (#170)
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1362 |
| CritPt | — | 0.8% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| LiveBench | 29.6% | — |
Math Not comparable
Amazon Nova Micro: 26.9 (#254), Mercury 2: —
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
| LMArena Math | 1206 | — |
Knowledge Mercury 2 leads
Amazon Nova Micro: 29.6 (#237), Mercury 2: 36.2 (#172)
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 12.3% |
| LMArena Expert | 1184 | 1358 |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual Mercury 2 leads
Amazon Nova Micro: 36.5 (#239), Mercury 2: 46.6 (#157)
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1186 | 1331 |
| LMArena Chinese | 1209 | 1417 |
| LMArena Russian | 1185 | 1304 |
| LMArena French | 1238 | — |
| LMArena German | 1192 | — |
| LMArena Japanese | 1154 | — |
| LMArena Korean | 1150 | — |
| LMArena Spanish | 1225 | — |
Instruction Following Mercury 2 leads
Amazon Nova Micro: 56.3 (#272), Mercury 2: 70.2 (#165)
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1329 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Mercury 2 leads
Amazon Nova Micro: 36.5 (#229), Mercury 2: 40.5 (#154)
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1205 | 1330 |
Writing & Preference Mercury 2 leads
Amazon Nova Micro: 39.5 (#247), Mercury 2: 53.8 (#155)
| Benchmark | Amazon Nova Micro | Mercury 2 |
|---|---|---|
| LMArena Text | 1208 | 1355 |
| LMArena Creative Writing | 1172 | 1289 |
| LMArena Multi-Turn | 1178 | 1358 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 30.4 on the Noometry Index. Amazon Nova Micro costs 6.1× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Mercury 2?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is Amazon Nova Micro or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Amazon Nova Micro and Mercury 2 share?
12 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Mercury 2 has 17.