Model comparison
Qwen3.6 35B-A3B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 37.6 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 4 benchmarks with published results for both. Qwen3.6 35B-A3B scores higher in 4 categories and Trinity Large Thinking in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 35B-A3B leads 28.0 to 16.9.
- The biggest single-benchmark swing is Surface Evolver Bench: 44.4% for Qwen3.6 35B-A3B and 15.6% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.25 / $1.49 for Qwen3.6 35B-A3B.
Side by side
| Qwen3.6 35B-A3B | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 37.6 | 38.6 |
| Released | 2026-04-01 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 66K | 80K |
| Input $ / M tokens | $0.25 | $0.25 |
| Output $ / M tokens | $1.49 | $0.80 |
| Results tracked | 14 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 37.2 (#196), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| SciCode | 35.8% | 36.1% |
| LMArena WebDev | — | 1238 |
| WeirdML | 34.5% | — |
| LMArena Coding | — | 1381 |
Agentic & Tool Use Not comparable
Qwen3.6 35B-A3B: 22.1 (#134), Trinity Large Thinking: —
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| Terminal-Bench | 23% | — |
Reasoning Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 28.0 (#109), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 41.6% | 16.5% |
| CritPt | 0.3% | 0.9% |
| Surface Evolver Bench | 44.4% | 15.6% |
| Chess Puzzles | 26% | — |
| Thematic Generalization | — | 41.6% |
| LMArena Hard Prompts | — | 1350 |
| Mystery Game Puzzles | 22% | — |
| DTBench | 73.9% | — |
| LMCA | 29.7% | — |
| Epoch Capabilities Index | 143.93 | — |
Math Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 38.9 (#121), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20.4% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| LMArena Math | — | 1366 |
Knowledge Qwen3.6 35B-A3B leads
Qwen3.6 35B-A3B: 51.3 (#68), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| GPQA Diamond | 84.8% | — |
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1360 |
Multilingual Not comparable
Qwen3.6 35B-A3B: —, Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | — | 1325 |
| LMArena Chinese | — | 1373 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1337 |
| LMArena Spanish | — | 1357 |
Instruction Following Not comparable
Qwen3.6 35B-A3B: —, Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | — | 1334 |
Long Context Not comparable
Qwen3.6 35B-A3B: —, Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | — | 1355 |
Writing & Preference Not comparable
Qwen3.6 35B-A3B: —, Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen3.6 35B-A3B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1320 |
| LMArena Multi-Turn | — | 1342 |
Frequently asked questions
Is Qwen3.6 35B-A3B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 37.6 on the Noometry Index.
Which is cheaper, Qwen3.6 35B-A3B or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Qwen3.6 35B-A3B lists at $0.25 and $1.49.
Is Qwen3.6 35B-A3B or Trinity Large Thinking better for coding?
Qwen3.6 35B-A3B scores higher on coding benchmarks: 37.2 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Qwen3.6 35B-A3B and Trinity Large Thinking share?
4 benchmarks have published results for both models. Qwen3.6 35B-A3B has 14 scored results on Noometry and Trinity Large Thinking has 24.