Nova Lite 1.0 vs Mercury 2.5
Mercury 2.5 leads Nova Lite 1.0 on the Artificial Analysis Intelligence Index, 12.3 to 6.7, and Mercury 2.5 costs 1.6x less per output token ($0.15 vs $0.24 per million). Updated October 21, 2026; 3 benchmarks have a result for both.
Nova Lite 1.0 or Mercury 2.5: which to pick
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; Nova Lite 1.0 has none, so the two cannot be ranked on coding.
Pick Nova Lite 1.0 for a larger context window (300K against 260K tokens).
- Shared results
- 3
- Nova Lite 1.0 only
- 38
- Mercury 2.5 only
- 19
- Like-for-like categories
- 3 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
Only Mercury 2.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Mercury 2.5
Mercury 2.5 leads, 12.3 against 6.7.
Same board, both measured
Long documents
Listed context window
Nova Lite 1.0
Nova Lite 1.0 takes 300K tokens against 260K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2.5
Nova Lite 1.0 $0.0002, Mercury 2.5 $0.0001 per turn.
List prices
At a glance
- Coding index
- Nova Lite 1.0 not benchmarked, Mercury 2.5 1.6 from 2 benchmarks.
- Widest category
- General, 52.7 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Nova Lite 1.0 19.0% against Mercury 2.5 71.7%, 52.7 points apart on a 0 to 100 scale.
- Output price
- Nova Lite 1.0 $0.24 against Mercury 2.5 $0.15 per million output tokens, 1.6x apart.
- Context window
- Nova Lite 1.0 takes 300K tokens, Mercury 2.5 260K.
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 2.5 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 3 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index13 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | Leader |
|---|---|---|---|
| Terminal-Bench 4 (Vals AI) | Not measured | 0.0% | Only Mercury 2.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 3.7% | Only Mercury 2.5 measured |
| Code migration (Vals AI) | Not measured | 4.5% | Only Mercury 2.5 measured |
| IOI (Vals AI) | Not measured | 2.4% | Only Mercury 2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 34.5% | Only Mercury 2.5 measured |
| SkillsBench (Vals AI) | Not measured | 18.1% | Only Mercury 2.5 measured |
| CyberBench (Vals AI) | Not measured | 45.5% | Only Mercury 2.5 measured |
| LiveCodeBench (Artificial Analysis run) | 16.7% | Not measured | Only Nova Lite 1.0 measured |
| SciCode | Not measured | 38.5% | Only Mercury 2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 0.8% | Not measured | Only Nova Lite 1.0 measured |
| ALE-Bench | Not measured | 301.6 | Only Mercury 2.5 measured |
| LMArena Text: coding | 1239 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: software and IT | 1241 | Not measured | Only Nova Lite 1.0 measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 12.3 | Mercury 2.5 |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | Not measured | 18.9% | Only Mercury 2.5 measured |
| Tax Agent Bench (Vals AI) | Not measured | 2.5% | Only Mercury 2.5 measured |
| Legal Research Bench (Vals AI) | Not measured | 4.3% | Only Mercury 2.5 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 8.8% | Only Mercury 2.5 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 0.0% | Only Mercury 2.5 measured |
| τ²-Bench Telecom | 17.5% | Not measured | Only Nova Lite 1.0 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 43.3% | Not measured | Only Nova Lite 1.0 measured |
| Humanity's Last Exam (Artificial Analysis run) | 4.3% | 11.8% | Mercury 2.5 |
| LMArena Text: hard prompts | 1220 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: expert | 1201 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: hard prompts in English | 1226 | Not measured | Only Nova Lite 1.0 measured |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | 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 |
| ProofBench | Not measured | 3.0% | Only Mercury 2.5 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 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | Not measured | 83.1% | Only Mercury 2.5 measured |
| MedCode (Vals AI) | Not measured | 31.3% | Only Mercury 2.5 measured |
| 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 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: medicine and healthcare | 1213 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: legal and government | 1238 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: business and finance | 1219 | Not measured | Only Nova Lite 1.0 measured |
| Neither model has a result on the other 9 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 45.3% | Only Mercury 2.5 measured |
| MedScribe (Vals AI) | Not measured | 55.1% | Only Mercury 2.5 measured |
| IFBench | 34.1% | Not measured | Only Nova Lite 1.0 measured |
| Long context reasoning (AA-LCR) | 19.0% | 71.7% | Mercury 2.5 |
| LMArena Text | 1229 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: instruction following | 1205 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: creative writing | 1197 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Vision | 990 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: English | 1243 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: non-English | 1208 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: Chinese | 1225 | Not measured | Only Nova Lite 1.0 measured |
| 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 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: multi-turn | 1199 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: longer queries | 1234 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: writing and language | 1211 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Text: entertainment and media | 1176 | Not measured | Only Nova Lite 1.0 measured |
| LMArena Vision: English | 999 | Not measured | Only Nova Lite 1.0 measured |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Lite 1.0 | Mercury 2.5 | 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
Mercury 2.5 costs less
Repository review
50K input + 3K output tokens
Mercury 2.5 costs less
Agent loop
200K input + 10K output tokens
Mercury 2.5 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 2.5 |
|---|---|---|
| Maker | Amazon | Inception |
| Weights | No public weights listed | No public weights listed |
| Released | December 5, 2024 | September 8, 2026 |
| Context window | 300K | 260K |
| Input $/Mtok | $0.06 | $0.04 |
| Output $/Mtok | $0.24 | $0.15 |
| Coding index | Not benchmarked | 1.6 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nova Lite 1.0 better than Mercury 2.5 for coding?
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; Nova Lite 1.0 has none, so the two cannot be ranked on coding. Pick Nova Lite 1.0 for a larger context window (300K against 260K tokens).
Which is cheaper, Nova Lite 1.0 or Mercury 2.5?
Nova Lite 1.0 costs $0.06 per million input tokens and $0.24 per million output tokens; Mercury 2.5 costs $0.04 and $0.15. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova Lite 1.0 or Mercury 2.5?
Nova Lite 1.0, with 300K tokens against 260K.
How many benchmarks is the Nova Lite 1.0 vs Mercury 2.5 comparison based on?
3 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 2.5's on 2. Where only one model has a result, the page says so instead of naming a winner.