Model comparison
Qwen3.6 Max Preview vs Trinity Large Thinking
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 38.6 on the Noometry Index. Trinity Large Thinking costs 7.5× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 16 benchmarks with published results for both. Qwen3.6 Max Preview scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 Max Preview leads 41.7 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 74.1% for Qwen3.6 Max Preview and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Qwen3.6 Max Preview | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 51.5 | 38.6 |
| Released | 2026-04-20 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 262K | 262K |
| Max output | 66K | 80K |
| Input $ / M tokens | $1.30 | $0.25 |
| Output $ / M tokens | $7.80 | $0.80 |
| Results tracked | 29 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 48.7 (#54), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1482 | 1238 |
| LMArena Coding | 1471 | 1381 |
| SWE-bench Verified | 76.7% | — |
| SciCode | — | 36.1% |
Agentic & Tool Use Not comparable
Qwen3.6 Max Preview: —, Trinity Large Thinking: —
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| Vending-Bench 2 | 4,254 | — |
Reasoning Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 41.7 (#53), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 74.1% | 16.5% |
| LMArena Hard Prompts | 1457 | 1350 |
| SimpleBench | 63% | — |
| CritPt | — | 0.9% |
| Chess Puzzles | 20% | — |
| Thematic Generalization | — | 41.6% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 87.2% | — |
| LMCA | 42.5% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 149.24 | — |
Math Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 54.1 (#46), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1465 | 1366 |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| FrontierMath (Feb 2025 set) | 23.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 57.6 (#39), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1478 | 1360 |
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 52% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 54.2 (#48), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1437 | 1325 |
| LMArena Chinese | 1487 | 1373 |
| LMArena French | 1449 | 1374 |
| LMArena Russian | 1445 | 1337 |
| LMArena Spanish | 1454 | 1357 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
Instruction Following Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 75.7 (#55), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1438 | 1334 |
Long Context Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 44.6 (#61), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1457 | 1355 |
Writing & Preference Qwen3.6 Max Preview leads
Qwen3.6 Max Preview: 63.8 (#60), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen3.6 Max Preview | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1447 | 1340 |
| LMArena Creative Writing | 1435 | 1320 |
| LMArena Multi-Turn | 1456 | 1342 |
Frequently asked questions
Is Qwen3.6 Max Preview better than Trinity Large Thinking?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 38.6 on the Noometry Index. Trinity Large Thinking costs 7.5× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Qwen3.6 Max Preview 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 Max Preview lists at $1.30 and $7.80.
Is Qwen3.6 Max Preview or Trinity Large Thinking better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Qwen3.6 Max Preview and Trinity Large Thinking share?
16 benchmarks have published results for both models. Qwen3.6 Max Preview has 29 scored results on Noometry and Trinity Large Thinking has 24.