Nova Lite 1.0 vs Mercury 2
Mercury 2 leads Nova Lite 1.0 on the Artificial Analysis Intelligence Index, 10.8 to 6.7, and Nova Lite 1.0 costs 3.1x less per output token ($0.24 vs $0.75 per million). Updated October 21, 2026; 26 benchmarks have a result for both.
Nova Lite 1.0 or Mercury 2: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Nova Lite 1.0 for output tokens 3.1x cheaper ($0.24 vs $0.75 per million) and a larger context window (300K against 128K tokens).
- Shared results
- 26
- Nova Lite 1.0 only
- 15
- Mercury 2 only
- 16
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Mercury 2
Mercury 2 leads, 10.8 against 6.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mercury 2 has a AA Agentic Index result, 1.6.
Directional only
Web design
Design Arena: websites
No call
Only Mercury 2 has a Design Arena: websites result, 1036.
Directional only
Long documents
Listed context window
Nova Lite 1.0
Nova Lite 1.0 takes 300K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nova Lite 1.0
Nova Lite 1.0 $0.0002, Mercury 2 $0.0006 per turn.
List prices
At a glance
- Coding index
- Nova Lite 1.0 not benchmarked, Mercury 2 not benchmarked.
- Widest category
- Agentic work, 53.2 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Nova Lite 1.0 17.5% against Mercury 2 70.8%, 53.2 points apart on a 0 to 100 scale.
- Output price
- Nova Lite 1.0 $0.24 against Mercury 2 $0.75 per million output tokens, 3.1x apart.
- Context window
- Nova Lite 1.0 takes 300K tokens, Mercury 2 128K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Nova Lite 1.0 | Bars | Mercury 2 | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 5 | ||
| Knowledge | 0 | 3 | ||
| General | 0 | 13 | ||
| All shared boards | 0 | 26 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1171 | Only Mercury 2 measured |
| AA Coding Index | Not measured | 31.1 | Only Mercury 2 measured |
| LiveCodeBench (Artificial Analysis run) | 16.7% | Not measured | Only Nova Lite 1.0 measured |
| SciCode | Not measured | 37.7% | Only Mercury 2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 0.8% | 26.5% | Mercury 2 |
| WeirdML | Not measured | 43.2% | Only Mercury 2 measured |
| ALE-Bench | Not measured | 785.6 | Only Mercury 2 measured |
| LMArena Text: coding | 1239 | 1390 | Mercury 2 |
| LMArena Text: software and IT | 1241 | 1385 | Mercury 2 |
| LMArena WebDev: React | Not measured | 1160 | Only Mercury 2 measured |
| LMArena WebDev: HTML | Not measured | 1199 | Only Mercury 2 measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 10.8 | Mercury 2 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.6 | Only Mercury 2 measured |
| τ²-Bench Telecom | 17.5% | 70.8% | Mercury 2 |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 43.3% | 77.0% | Mercury 2 |
| Humanity's Last Exam (Artificial Analysis run) | 4.3% | 17.1% | Mercury 2 |
| LMArena Text: hard prompts | 1220 | 1362 | Mercury 2 |
| LMArena Text: expert | 1201 | 1358 | Mercury 2 |
| LMArena Text: hard prompts in English | 1226 | 1374 | Mercury 2 |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| AA Math Index | 7.0 | Not measured | Only Nova Lite 1.0 measured |
| AIME 2025 (Artificial Analysis run) | 7.0% | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: math | 1227 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: mathematical work | 1235 | Not measured | Only Nova Lite 1.0 measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 59.0% | Not measured | Only Nova Lite 1.0 measured |
| MMLU | 77.0% | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: science | 1232 | 1343 | Mercury 2 |
| LMArena Text: medicine and healthcare | 1213 | 1363 | Mercury 2 |
| LMArena Text: legal and government | 1238 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: business and finance | 1219 | 1349 | Mercury 2 |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1036 | Only Mercury 2 measured |
| Design Arena: UI components | Not measured | 998 | Only Mercury 2 measured |
| Design Arena: game dev | Not measured | 985 | Only Mercury 2 measured |
| Design Arena: data viz | Not measured | 1009 | Only Mercury 2 measured |
| Design Arena: 3D | Not measured | 983 | Only Mercury 2 measured |
| Design Arena: all code categories | Not measured | 1022 | Only Mercury 2 measured |
| Design Arena: SVG | Not measured | 998 | Only Mercury 2 measured |
| Design Arena: ASCII art | Not measured | 988 | Only Mercury 2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| IFBench | 34.1% | 69.8% | Mercury 2 |
| Long context reasoning (AA-LCR) | 19.0% | 43.7% | Mercury 2 |
| LMArena Text | 1229 | 1354 | Mercury 2 |
| LMArena Text: instruction following | 1205 | 1328 | Mercury 2 |
| LMArena Text: creative writing | 1197 | 1286 | Mercury 2 |
| LMArena Vision | 990 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: English | 1243 | 1378 | Mercury 2 |
| LMArena Text: non-English | 1208 | 1330 | Mercury 2 |
| LMArena Text: Chinese | 1225 | 1414 | Mercury 2 |
| LMArena Text: German | 1229 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: Japanese | 1153 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: Korean | 1153 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: French | 1238 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: Spanish | 1226 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: Russian | 1216 | 1304 | Mercury 2 |
| LMArena Text: multi-turn | 1199 | 1357 | Mercury 2 |
| LMArena Text: longer queries | 1234 | 1329 | Mercury 2 |
| LMArena Text: writing and language | 1211 | 1300 | Mercury 2 |
| LMArena Text: entertainment and media | 1176 | 1314 | Mercury 2 |
| LMArena Vision: English | 999 | Not measured | Only Nova Lite 1.0 measured |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Nova Lite 1.0 costs less
Repository review
50K input + 3K output tokens
Nova Lite 1.0 costs less
Agent loop
200K input + 10K output tokens
Nova Lite 1.0 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Amazon Nova Lite 1.0 | Inception Mercury 2 |
|---|---|---|
| Maker | Amazon | Inception |
| Weights | No public weights listed | No public weights listed |
| Released | December 5, 2024 | March 4, 2026 |
| Context window | 300K | 128K |
| Input $/Mtok | $0.06 | $0.25 |
| Output $/Mtok | $0.24 | $0.75 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nova Lite 1.0 better than Mercury 2 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova Lite 1.0 for output tokens 3.1x cheaper ($0.24 vs $0.75 per million) and a larger context window (300K against 128K tokens).
Which is cheaper, Nova Lite 1.0 or Mercury 2?
Nova Lite 1.0 costs $0.06 per million input tokens and $0.24 per million output tokens; Mercury 2 costs $0.25 and $0.75. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova Lite 1.0 or Mercury 2?
Nova Lite 1.0, with 300K tokens against 128K.
How many benchmarks is the Nova Lite 1.0 vs Mercury 2 comparison based on?
26 benchmarks have a result for both models as of October 21, 2026. Nova Lite 1.0's coding index rests on 0 independent benchmarks and Mercury 2's on 1. Where only one model has a result, the page says so instead of naming a winner.