Trinity Large Thinking vs Mercury 2
Trinity Large Thinking and Mercury 2 tie on the Artificial Analysis Intelligence Index at 10.8, at about the same output price ($0.80 vs $0.75 per million). Updated October 22, 2026; 40 benchmarks have a result for both.
Trinity Large Thinking or Mercury 2: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Trinity Large Thinking for a larger context window (262K against 128K tokens) and work measured by AA Coding Index or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 40
- Trinity Large Thinking only
- 12
- Mercury 2 only
- 2
- 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
No call
Tied at 10.8.
Same board, both measured
Agentic work
AA Agentic Index
Mercury 2
Mercury 2 leads, 1.6 against 1.0.
Same board, both measured
Web design
Design Arena: websites
Trinity Large Thinking
Trinity Large Thinking leads, 1137 against 1036.
Same board, both measured
Long documents
Listed context window
Trinity Large Thinking
Trinity Large Thinking takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2
Trinity Large Thinking $0.0006, Mercury 2 $0.0006 per turn.
List prices
At a glance
- Coding index
- Trinity Large Thinking not benchmarked, Mercury 2 not benchmarked.
- Widest category
- Agentic work, 9.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: Trinity Large Thinking 90.1% against Mercury 2 70.8%, 19.3 points apart on a 0 to 100 scale.
- Output price
- Trinity Large Thinking $0.80 against Mercury 2 $0.75 per million output tokens, 1.1x apart.
- Context window
- Trinity Large Thinking takes 262K 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 | Trinity Large Thinking | Bars | Mercury 2 | Ties |
|---|---|---|---|---|
| Coding | 4 | 4 | ||
| Intelligence | 0 | 0 | 1 tie | |
| Agentic work | 1 | 1 | ||
| Reasoning | 1 | 4 | ||
| Knowledge | 1 | 2 | ||
| Web design | 8 | 0 | ||
| General | 3 | 10 | ||
| All shared boards | 18 | 21 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index44
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| LMArena WebDev | 1238 | 1171 | Trinity Large Thinking |
| AA Coding Index | 25.8 | 31.1 | Mercury 2 |
| SciCode | 40.6% | 37.7% | Trinity Large Thinking |
| Terminal-Bench Hard (Artificial Analysis run) | 22.7% | 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 | 1357 | 1390 | Mercury 2 |
| LMArena Text: software and IT | 1362 | 1385 | Mercury 2 |
| LMArena WebDev: React | 1231 | 1160 | Trinity Large Thinking |
| LMArena WebDev: HTML | 1240 | 1199 | Trinity Large Thinking |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index00
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 10.8 | Tie |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| AA Agentic Index | 1.0 | 1.6 | Mercury 2 |
| τ²-Bench Telecom | 90.1% | 70.8% | Trinity Large Thinking |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 75.2% | 77.0% | Mercury 2 |
| Humanity's Last Exam (Artificial Analysis run) | 15.8% | 17.1% | Mercury 2 |
| LMArena Text: hard prompts | 1342 | 1362 | Mercury 2 |
| LMArena Text: expert | 1359 | 1358 | Trinity Large Thinking |
| LMArena Text: hard prompts in English | 1356 | 1374 | Mercury 2 |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| LMArena Text: math | 1365 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: mathematical work | 1350 | Not measured | Only Trinity Large Thinking measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 57.9% | Not measured | Only Trinity Large Thinking measured |
| CorpFin (Vals AI) | 54.7% | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: science | 1355 | 1343 | Trinity Large Thinking |
| LMArena Text: medicine and healthcare | 1349 | 1363 | Mercury 2 |
| LMArena Text: legal and government | 1345 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: business and finance | 1329 | 1349 | Mercury 2 |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| Design Arena: websites | 1137 | 1036 | Trinity Large Thinking |
| Design Arena: UI components | 1042 | 996 | Trinity Large Thinking |
| Design Arena: game dev | 1078 | 984 | Trinity Large Thinking |
| Design Arena: data viz | 1098 | 1009 | Trinity Large Thinking |
| Design Arena: 3D | 1081 | 982 | Trinity Large Thinking |
| Design Arena: all code categories | 1117 | 1021 | Trinity Large Thinking |
| Design Arena: SVG | 1016 | 998 | Trinity Large Thinking |
| Design Arena: ASCII art | 1041 | 988 | Trinity Large Thinking |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index310
| Benchmark | Trinity Large Thinking | Mercury 2 | Leader |
|---|---|---|---|
| IFBench | 56.3% | 69.8% | Mercury 2 |
| Long context reasoning (AA-LCR) | 38.0% | 43.7% | Mercury 2 |
| Surface Evolver Bench | 15.6% | Not measured | Only Trinity Large Thinking measured |
| LMArena Text | 1340 | 1354 | Mercury 2 |
| LMArena Text: instruction following | 1326 | 1328 | Mercury 2 |
| LMArena Text: creative writing | 1308 | 1286 | Trinity Large Thinking |
| LMArena Text: English | 1356 | 1378 | Mercury 2 |
| LMArena Text: non-English | 1325 | 1330 | Mercury 2 |
| LMArena Text: Chinese | 1371 | 1414 | Mercury 2 |
| LMArena Text: German | 1356 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Japanese | 1312 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Korean | 1306 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: French | 1366 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Spanish | 1327 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Russian | 1338 | 1304 | Trinity Large Thinking |
| LMArena Text: Polish | 1312 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: multi-turn | 1320 | 1357 | Mercury 2 |
| LMArena Text: longer queries | 1318 | 1329 | Mercury 2 |
| LMArena Text: writing and language | 1317 | 1300 | Trinity Large Thinking |
| LMArena Text: entertainment and media | 1296 | 1314 | Mercury 2 |
| 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 | Trinity Large Thinking | 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
Mercury 2 costs less
Repository review
50K input + 3K output tokens
Mercury 2 costs less
Agent loop
200K input + 10K output tokens
Mercury 2 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 | Arcee AI Trinity Large Thinking | Inception Mercury 2 |
|---|---|---|
| Maker | Arcee AI | Inception |
| Weights | Open weights | No public weights listed |
| Released | April 1, 2026 | March 4, 2026 |
| Context window | 262K | 128K |
| Input $/Mtok | $0.25 | $0.25 |
| Output $/Mtok | $0.80 | $0.75 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Trinity Large Thinking better than Mercury 2 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Trinity Large Thinking for a larger context window (262K against 128K tokens) and work measured by AA Coding Index or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, Trinity Large Thinking or Mercury 2?
Trinity Large Thinking costs $0.25 per million input tokens and $0.80 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, Trinity Large Thinking or Mercury 2?
Trinity Large Thinking, with 262K tokens against 128K.
How many benchmarks is the Trinity Large Thinking vs Mercury 2 comparison based on?
40 benchmarks have a result for both models as of October 22, 2026. Trinity Large Thinking's coding index rests on 1 independent benchmark and Mercury 2's on 1. Where only one model has a result, the page says so instead of naming a winner.