# Amazon Nova Pro vs Mercury 2

> Mercury 2 is the stronger model overall, scoring 39.1 to 31.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Mercury 2 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 43.9.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Amazon Nova Pro and 12.3% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.

## Snapshot

| | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| Provider | Amazon | Inception |
| Noometry Index | 31.0 | 39.1 |
| Rank | 281 | 175 |
| Context | 300K | 128K |
| Input $/M | $0.80 | $0.25 |
| Output $/M | $3.20 | $0.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Mercury 2: 33.5 (#255)

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| LMArena Coding | 1270 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 785.58 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Mercury 2: —

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Mercury 2: 23.8 (#170)

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1362 |
| CritPt | — | 0.8% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Mercury 2: —

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| LMArena Math | 1252 | — |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Mercury 2: 36.2 (#172)

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 12.3% |
| LMArena Expert | 1211 | 1358 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Mercury 2: —

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Mercury 2: 46.6 (#157)

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1234 | 1331 |
| LMArena Chinese | 1244 | 1417 |
| LMArena Russian | 1240 | 1304 |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1182 | — |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Mercury 2: 70.2 (#165)

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1329 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Mercury 2: 40.5 (#154)

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1255 | 1330 |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Mercury 2: 53.8 (#155)

| Benchmark | Amazon Nova Pro | Mercury 2 |
|---|---|---|
| LMArena Text | 1259 | 1355 |
| LMArena Creative Writing | 1212 | 1289 |
| LMArena Multi-Turn | 1246 | 1358 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 39.1 to 31.0 on the Noometry Index.

### Which is cheaper, Amazon Nova Pro or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or Mercury 2 better for coding?

Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 128K.

### How many benchmarks do Amazon Nova Pro and Mercury 2 share?

12 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Mercury 2 has 17.