Trinity Large Thinking vs Qwen3.5-35B-A3B
Qwen3.5-35B-A3B leads Trinity Large Thinking on the Artificial Analysis Intelligence Index, 19.3 to 10.8, and Trinity Large Thinking costs 1.6x less per output token ($0.80 vs $1.30 per million). Updated October 22, 2026; 38 benchmarks have a result for both.
Trinity Large Thinking or Qwen3.5-35B-A3B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Trinity Large Thinking for output tokens 1.6x cheaper ($0.80 vs $1.30 per million) and work measured by LMArena WebDev or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 38
- Trinity Large Thinking only
- 14
- Qwen3.5-35B-A3B only
- 7
- 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
Qwen3.5-35B-A3B
Qwen3.5-35B-A3B leads, 19.3 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
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Trinity Large Thinking
Trinity Large Thinking $0.0006, Qwen3.5-35B-A3B $0.0008 per turn.
List prices
At a glance
- Coding index
- Trinity Large Thinking not benchmarked, Qwen3.5-35B-A3B not benchmarked.
- Widest category
- Knowledge, 10.4 points apart on average over 4 shared benchmarks.
- Widest single gap
- Long context reasoning (AA-LCR): Trinity Large Thinking 38.0% against Qwen3.5-35B-A3B 72.0%, 34.0 points apart on a 0 to 100 scale.
- Output price
- Trinity Large Thinking $0.80 against Qwen3.5-35B-A3B $1.30 per million output tokens, 1.6x apart.
- Context window
- Both take 262K 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 | Trinity Large Thinking | Bars | Qwen3.5-35B-A3B | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 19 | ||
| All shared boards | 1 | 37 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | Leader |
|---|---|---|---|
| LMArena WebDev | 1238 | 1254 | Qwen3.5-35B-A3B |
| AA Coding Index | 25.8 | Not measured | Only Trinity Large Thinking measured |
| SciCode | 40.6% | Not measured | Only Trinity Large Thinking measured |
| Terminal-Bench Hard (Artificial Analysis run) | 22.7% | 26.5% | Qwen3.5-35B-A3B |
| ALE-Bench | Not measured | 221.8 | Only Qwen3.5-35B-A3B measured |
| LMArena Text: coding | 1357 | 1410 | Qwen3.5-35B-A3B |
| LMArena Text: software and IT | 1362 | 1415 | Qwen3.5-35B-A3B |
| LMArena WebDev: React | 1231 | 1238 | Qwen3.5-35B-A3B |
| LMArena WebDev: HTML | 1240 | 1301 | Qwen3.5-35B-A3B |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 19.3 | Qwen3.5-35B-A3B |
| Epoch Capabilities Index | Not measured | 142.5 | Only Qwen3.5-35B-A3B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | Leader |
|---|---|---|---|
| AA Agentic Index | 1.0 | Not measured | Only Trinity Large Thinking measured |
| τ²-Bench Telecom | 90.1% | 89.2% | Trinity Large Thinking |
| Vending-Bench 2 | Not measured | $463 | Only Qwen3.5-35B-A3B measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 75.2% | 84.5% | Qwen3.5-35B-A3B |
| Humanity's Last Exam (Artificial Analysis run) | 15.8% | 21.0% | Qwen3.5-35B-A3B |
| GPQA Diamond (Epoch AI run) | Not measured | 83.5% | Only Qwen3.5-35B-A3B measured |
| LMArena Text: hard prompts | 1342 | 1400 | Qwen3.5-35B-A3B |
| LMArena Text: expert | 1359 | 1408 | Qwen3.5-35B-A3B |
| LMArena Text: hard prompts in English | 1356 | 1411 | Qwen3.5-35B-A3B |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 70.0% | Only Qwen3.5-35B-A3B measured |
| LMArena Text: math | 1365 | 1404 | Qwen3.5-35B-A3B |
| LMArena Text: mathematical work | 1350 | 1410 | Qwen3.5-35B-A3B |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | 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 | 1413 | Qwen3.5-35B-A3B |
| LMArena Text: medicine and healthcare | 1349 | 1421 | Qwen3.5-35B-A3B |
| LMArena Text: legal and government | 1345 | 1399 | Qwen3.5-35B-A3B |
| LMArena Text: business and finance | 1329 | 1394 | Qwen3.5-35B-A3B |
| Neither model has a result on the other 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | Leader |
|---|---|---|---|
| Design Arena: websites | 1137 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: UI components | 1042 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: game dev | 1078 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: data viz | 1098 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: 3D | 1081 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: all code categories | 1117 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: SVG | 1016 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: ASCII art | 1041 | Not measured | 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 index019
| Benchmark | Trinity Large Thinking | Qwen3.5-35B-A3B | Leader |
|---|---|---|---|
| IFBench | 56.3% | 72.5% | Qwen3.5-35B-A3B |
| Long context reasoning (AA-LCR) | 38.0% | 72.0% | Qwen3.5-35B-A3B |
| DTBench | Not measured | 80.0% | Only Qwen3.5-35B-A3B measured |
| LMCA | Not measured | 29.5% | Only Qwen3.5-35B-A3B measured |
| Surface Evolver Bench | 15.6% | Not measured | Only Trinity Large Thinking measured |
| LMArena Text | 1340 | 1395 | Qwen3.5-35B-A3B |
| LMArena Text: instruction following | 1326 | 1379 | Qwen3.5-35B-A3B |
| LMArena Text: creative writing | 1308 | 1347 | Qwen3.5-35B-A3B |
| LMArena Text: English | 1356 | 1407 | Qwen3.5-35B-A3B |
| LMArena Text: non-English | 1325 | 1378 | Qwen3.5-35B-A3B |
| LMArena Text: Chinese | 1371 | 1457 | Qwen3.5-35B-A3B |
| LMArena Text: German | 1356 | 1367 | Qwen3.5-35B-A3B |
| LMArena Text: Japanese | 1312 | 1326 | Qwen3.5-35B-A3B |
| LMArena Text: Korean | 1306 | 1355 | Qwen3.5-35B-A3B |
| LMArena Text: French | 1366 | 1412 | Qwen3.5-35B-A3B |
| LMArena Text: Spanish | 1327 | 1390 | Qwen3.5-35B-A3B |
| LMArena Text: Russian | 1338 | 1376 | Qwen3.5-35B-A3B |
| LMArena Text: Polish | 1312 | 1385 | Qwen3.5-35B-A3B |
| LMArena Text: multi-turn | 1320 | 1390 | Qwen3.5-35B-A3B |
| LMArena Text: longer queries | 1318 | 1389 | Qwen3.5-35B-A3B |
| LMArena Text: writing and language | 1317 | 1365 | Qwen3.5-35B-A3B |
| LMArena Text: entertainment and media | 1296 | 1347 | Qwen3.5-35B-A3B |
| 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 | Trinity Large Thinking | Qwen3.5-35B-A3B | 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
Qwen3.5-35B-A3B costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-35B-A3B 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 | Qwen3.5-35B-A3B |
|---|---|---|
| Maker | Arcee AI | Qwen |
| Weights | Open weights | Open weights |
| Released | April 1, 2026 | February 25, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.25 | $0.1625 |
| Output $/Mtok | $0.80 | $1.30 |
| 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 Qwen3.5-35B-A3B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Trinity Large Thinking for output tokens 1.6x cheaper ($0.80 vs $1.30 per million) and work measured by LMArena WebDev or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, Trinity Large Thinking or Qwen3.5-35B-A3B?
Trinity Large Thinking costs $0.25 per million input tokens and $0.80 per million output tokens; Qwen3.5-35B-A3B costs $0.1625 and $1.30. Cost per solved task is known for neither of them.
Which has the bigger context window, Trinity Large Thinking or Qwen3.5-35B-A3B?
Neither: both take 262K tokens.
How many benchmarks is the Trinity Large Thinking vs Qwen3.5-35B-A3B comparison based on?
38 benchmarks have a result for both models as of October 22, 2026. Trinity Large Thinking's coding index rests on 1 independent benchmark and Qwen3.5-35B-A3B's on 1. Where only one model has a result, the page says so instead of naming a winner.