Nova 2 Lite vs Trinity Large Thinking
Updated October 21, 2026. 30 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Nova 2 Lite has the edge where the context window is larger, 1M against 262K tokens, and where what matters is AA Coding Index or LMArena Text: expert, where it leads.
- Shared results
- 30
- Nova 2 Lite only
- 1
- Trinity Large Thinking only
- 22
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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 2 Lite
Nova 2 Lite leads, 13.4 against 10.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Trinity Large Thinking has a AA Agentic Index result, 1.0.
Directional only
Web design
Design Arena: websites
No call
Only Trinity Large Thinking has a Design Arena: websites result, 1137.
Directional only
Long documents
Listed context window
Nova 2 Lite
Nova 2 Lite takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Trinity Large Thinking
Nova 2 Lite $0.0015, Trinity Large Thinking $0.0006 per turn.
List prices
At a glance
- Coding index
- Nova 2 Lite not benchmarked, Trinity Large Thinking not benchmarked.
- Widest category
- Knowledge, 4.9 points apart on average over 4 shared benchmarks.
- Widest single gap
- LMArena Text: Spanish: Nova 2 Lite 1375 against Trinity Large Thinking 1327, 8.0 points apart on a 0 to 100 scale.
- Output price
- Nova 2 Lite $2.50 against Trinity Large Thinking $0.80 per million output tokens, 3.1x apart.
- Context window
- Nova 2 Lite takes 1M tokens, Trinity Large Thinking 262K.
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 2 Lite | Bars | Trinity Large Thinking | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 2 | 1 | ||
| Math | 1 | 1 | ||
| Knowledge | 4 | 0 | ||
| General | 12 | 5 | ||
| All shared boards | 22 | 8 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | Nova 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1238 | Only Trinity Large Thinking measured |
| AA Coding Index | 23.0 | 25.8 | Trinity Large Thinking |
| SciCode | Not measured | 40.6% | Only Trinity Large Thinking measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 22.7% | Only Trinity Large Thinking measured |
| ALE-Bench | 236.3 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: coding | 1385 | 1357 | Nova 2 Lite |
| LMArena Text: software and IT | 1394 | 1362 | Nova 2 Lite |
| LMArena WebDev: React | Not measured | 1231 | Only Trinity Large Thinking measured |
| LMArena WebDev: HTML | Not measured | 1240 | Only Trinity Large Thinking measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nova 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.4 | 10.8 | Nova 2 Lite |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Nova 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.0 | Only Trinity Large Thinking measured |
| τ²-Bench Telecom | Not measured | 90.1% | Only Trinity Large Thinking measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Nova 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 75.2% | Only Trinity Large Thinking measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 15.8% | Only Trinity Large Thinking measured |
| LMArena Text: hard prompts | 1364 | 1342 | Nova 2 Lite |
| LMArena Text: expert | 1359 | 1359 | Trinity Large Thinking |
| LMArena Text: hard prompts in English | 1385 | 1356 | Nova 2 Lite |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Nova 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| LMArena Text: math | 1359 | 1365 | Trinity Large Thinking |
| LMArena Text: mathematical work | 1369 | 1350 | Nova 2 Lite |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Nova 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | Not measured | 57.9% | Only Trinity Large Thinking measured |
| CorpFin (Vals AI) | Not measured | 54.7% | Only Trinity Large Thinking measured |
| LMArena Text: science | 1382 | 1355 | Nova 2 Lite |
| LMArena Text: medicine and healthcare | 1386 | 1349 | Nova 2 Lite |
| LMArena Text: legal and government | 1359 | 1345 | Nova 2 Lite |
| LMArena Text: business and finance | 1369 | 1329 | Nova 2 Lite |
| 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 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1137 | Only Trinity Large Thinking measured |
| Design Arena: UI components | Not measured | 1045 | Only Trinity Large Thinking measured |
| Design Arena: game dev | Not measured | 1079 | Only Trinity Large Thinking measured |
| Design Arena: data viz | Not measured | 1098 | Only Trinity Large Thinking measured |
| Design Arena: 3D | Not measured | 1082 | Only Trinity Large Thinking measured |
| Design Arena: all code categories | Not measured | 1117 | Only Trinity Large Thinking measured |
| Design Arena: SVG | Not measured | 1017 | Only Trinity Large Thinking measured |
| Design Arena: ASCII art | Not measured | 1041 | Only Trinity Large Thinking measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index125
| Benchmark | Nova 2 Lite | Trinity Large Thinking | Leader |
|---|---|---|---|
| IFBench | Not measured | 56.3% | Only Trinity Large Thinking measured |
| Long context reasoning (AA-LCR) | Not measured | 38.0% | Only Trinity Large Thinking measured |
| Surface Evolver Bench | Not measured | 15.6% | Only Trinity Large Thinking measured |
| LMArena Text | 1362 | 1340 | Nova 2 Lite |
| LMArena Text: instruction following | 1335 | 1326 | Nova 2 Lite |
| LMArena Text: creative writing | 1292 | 1308 | Trinity Large Thinking |
| LMArena Text: English | 1385 | 1356 | Nova 2 Lite |
| LMArena Text: non-English | 1337 | 1325 | Nova 2 Lite |
| LMArena Text: Chinese | 1364 | 1371 | Trinity Large Thinking |
| LMArena Text: German | 1343 | 1356 | Trinity Large Thinking |
| LMArena Text: Japanese | 1273 | 1312 | Trinity Large Thinking |
| LMArena Text: Korean | 1281 | 1306 | Trinity Large Thinking |
| LMArena Text: French | 1381 | 1366 | Nova 2 Lite |
| LMArena Text: Spanish | 1375 | 1327 | Nova 2 Lite |
| LMArena Text: Russian | 1342 | 1338 | Nova 2 Lite |
| LMArena Text: Polish | 1327 | 1312 | Nova 2 Lite |
| LMArena Text: multi-turn | 1338 | 1320 | Nova 2 Lite |
| LMArena Text: longer queries | 1335 | 1318 | Nova 2 Lite |
| LMArena Text: writing and language | 1318 | 1317 | Nova 2 Lite |
| LMArena Text: entertainment and media | 1309 | 1296 | Nova 2 Lite |
| 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 2 Lite | Trinity Large Thinking | 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
Trinity Large Thinking costs less
Repository review
50K input + 3K output tokens
Trinity Large Thinking costs less
Agent loop
200K input + 10K output tokens
Trinity Large Thinking 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 2 Lite | Arcee AI Trinity Large Thinking |
|---|---|---|
| Maker | Amazon | Arcee AI |
| Weights | No public weights listed | Open weights |
| Released | December 2, 2025 | April 1, 2026 |
| Context window | 1M | 262K |
| Input $/Mtok | $0.30 | $0.25 |
| Output $/Mtok | $2.50 | $0.80 |
| 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 2 Lite better than Trinity Large Thinking for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Nova 2 Lite has the edge where the context window is larger, 1M against 262K tokens, and where what matters is AA Coding Index or LMArena Text: expert, where it leads.
Which is cheaper, Nova 2 Lite or Trinity Large Thinking?
Nova 2 Lite costs $0.30 per million input tokens and $2.50 per million output tokens; Trinity Large Thinking costs $0.25 and $0.80. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova 2 Lite or Trinity Large Thinking?
Nova 2 Lite, with 1M tokens against 262K.
How many benchmarks is the Nova 2 Lite vs Trinity Large Thinking comparison based on?
30 benchmarks have a result for both models as of October 21, 2026. Nova 2 Lite's coding index rests on 0 independent benchmarks and Trinity Large Thinking's on 1. Where only one model has a result, the page says so instead of naming a winner.