Nova Lite 1.0 vs Nova Pro 1.0
Nova Pro 1.0 leads Nova Lite 1.0 on the Artificial Analysis Intelligence Index, 7.0 to 6.7, and Nova Lite 1.0 costs 13.3x less per output token ($0.24 vs $3.20 per million). Updated October 21, 2026; 41 benchmarks have a result for both.
Nova Lite 1.0 or Nova Pro 1.0: 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 13.3x cheaper ($0.24 vs $3.20 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 41
- Nova Lite 1.0 only
- 0
- Nova Pro 1.0 only
- 1
- Like-for-like categories
- 7 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
Nova Pro 1.0
Nova Pro 1.0 leads, 7.0 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Nova Pro 1.0 has a Design Arena: websites result, 796.
Directional only
Long documents
Listed context window
No call
Both take 300K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nova Lite 1.0
Nova Lite 1.0 $0.0002, Nova Pro 1.0 $0.0024 per turn.
List prices
At a glance
- Coding index
- Nova Lite 1.0 not benchmarked, Nova Pro 1.0 not benchmarked.
- Widest category
- Knowledge, 6.0 points apart on average over 6 shared benchmarks.
- Widest single gap
- MMLU Pro (Artificial Analysis run): Nova Lite 1.0 59.0% against Nova Pro 1.0 69.1%, 10.1 points apart on a 0 to 100 scale.
- Output price
- Nova Lite 1.0 $0.24 against Nova Pro 1.0 $3.20 per million output tokens, 13.3x apart.
- Context window
- Both take 300K tokens.
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 | Nova Pro 1.0 | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 1 | 4 | ||
| Math | 0 | 2 | 2 ties | |
| Knowledge | 0 | 6 | ||
| General | 3 | 17 | ||
| All shared boards | 5 | 34 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 16.7% | 23.3% | Nova Pro 1.0 |
| Terminal-Bench Hard (Artificial Analysis run) | 0.8% | 6.1% | Nova Pro 1.0 |
| LMArena Text: coding | 1239 | 1270 | Nova Pro 1.0 |
| LMArena Text: software and IT | 1241 | 1271 | Nova Pro 1.0 |
| Neither model has a result on the other 34 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 7.0 | Nova Pro 1.0 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 17.5% | 14.0% | Nova Lite 1.0 |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 43.3% | 49.9% | Nova Pro 1.0 |
| Humanity's Last Exam (Artificial Analysis run) | 4.3% | 3.2% | Nova Lite 1.0 |
| LMArena Text: hard prompts | 1220 | 1246 | Nova Pro 1.0 |
| LMArena Text: expert | 1201 | 1211 | Nova Pro 1.0 |
| LMArena Text: hard prompts in English | 1226 | 1259 | Nova Pro 1.0 |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| AA Math Index | 7.0 | 7.0 | Tie |
| AIME 2025 (Artificial Analysis run) | 7.0% | 7.0% | Tie |
| LMArena Text: math | 1227 | 1252 | Nova Pro 1.0 |
| LMArena Text: mathematical work | 1235 | 1261 | Nova Pro 1.0 |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 59.0% | 69.1% | Nova Pro 1.0 |
| MMLU | 77.0% | 82.0% | Nova Pro 1.0 |
| LMArena Text: science | 1232 | 1255 | Nova Pro 1.0 |
| LMArena Text: medicine and healthcare | 1213 | 1260 | Nova Pro 1.0 |
| LMArena Text: legal and government | 1238 | 1281 | Nova Pro 1.0 |
| LMArena Text: business and finance | 1219 | 1229 | Nova Pro 1.0 |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 796 | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index317
| Benchmark | Nova Lite 1.0 | Nova Pro 1.0 | Leader |
|---|---|---|---|
| IFBench | 34.1% | 38.1% | Nova Pro 1.0 |
| Long context reasoning (AA-LCR) | 19.0% | 21.0% | Nova Pro 1.0 |
| LMArena Text | 1229 | 1259 | Nova Pro 1.0 |
| LMArena Text: instruction following | 1205 | 1235 | Nova Pro 1.0 |
| LMArena Text: creative writing | 1197 | 1212 | Nova Pro 1.0 |
| LMArena Vision | 990 | 980 | Nova Lite 1.0 |
| LMArena Text: English | 1243 | 1276 | Nova Pro 1.0 |
| LMArena Text: non-English | 1208 | 1233 | Nova Pro 1.0 |
| LMArena Text: Chinese | 1225 | 1244 | Nova Pro 1.0 |
| LMArena Text: German | 1229 | 1243 | Nova Pro 1.0 |
| LMArena Text: Japanese | 1153 | 1200 | Nova Pro 1.0 |
| LMArena Text: Korean | 1153 | 1203 | Nova Pro 1.0 |
| LMArena Text: French | 1238 | 1271 | Nova Pro 1.0 |
| LMArena Text: Spanish | 1226 | 1182 | Nova Lite 1.0 |
| LMArena Text: Russian | 1216 | 1240 | Nova Pro 1.0 |
| LMArena Text: multi-turn | 1199 | 1246 | Nova Pro 1.0 |
| LMArena Text: longer queries | 1234 | 1255 | Nova Pro 1.0 |
| LMArena Text: writing and language | 1211 | 1247 | Nova Pro 1.0 |
| LMArena Text: entertainment and media | 1176 | 1210 | Nova Pro 1.0 |
| LMArena Vision: English | 999 | 987 | Nova Lite 1.0 |
| 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 | Nova Pro 1.0 | 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 | Amazon Nova Pro 1.0 |
|---|---|---|
| Maker | Amazon | Amazon |
| Weights | No public weights listed | No public weights listed |
| Released | December 5, 2024 | December 5, 2024 |
| Context window | 300K | 300K |
| Input $/Mtok | $0.06 | $0.80 |
| Output $/Mtok | $0.24 | $3.20 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nova Lite 1.0 better than Nova Pro 1.0 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 13.3x cheaper ($0.24 vs $3.20 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, Nova Lite 1.0 or Nova Pro 1.0?
Nova Lite 1.0 costs $0.06 per million input tokens and $0.24 per million output tokens; Nova Pro 1.0 costs $0.80 and $3.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova Lite 1.0 or Nova Pro 1.0?
Neither: both take 300K tokens.
How many benchmarks is the Nova Lite 1.0 vs Nova Pro 1.0 comparison based on?
41 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 Nova Pro 1.0's on 0. Where only one model has a result, the page says so instead of naming a winner.