Model comparison
Hy3 vs Trinity Large Thinking
Hy3 is the stronger model overall, scoring 43.6 to 38.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
Arcee AISummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 7 categories and Trinity Large Thinking in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.6 to 33.8.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 16.5% for Trinity Large Thinking.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
Side by side
| Hy3 | Trinity Large Thinking | |
|---|---|---|
| Provider | Tencent | Arcee AI |
| Noometry Index | 43.6 | 38.1 |
| Released | 2026-07-06 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 80K |
| Input $ / M tokens | $0.13 | $0.25 |
| Output $ / M tokens | $0.53 | $0.80 |
| Results tracked | 17 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Trinity Large Thinking: 33.8 (#238)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1509 | 1238 |
| LMArena Coding | 1465 | 1381 |
| SciCode | — | 36.1% |
Reasoning Hy3 leads
Hy3: 25.0 (#134), Trinity Large Thinking: 16.3 (#298)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 41.2% | 16.5% |
| LMArena Hard Prompts | 1449 | 1350 |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Hy3 leads
Hy3: 37.4 (#98), Trinity Large Thinking: 34.9 (#149)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1475 | 1366 |
Knowledge Too close to call
Hy3: 40.2 (#108), Trinity Large Thinking: 40.3 (#107)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1461 | 1359 |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Hy3 leads
Hy3: 53.7 (#60), Trinity Large Thinking: 46.4 (#155)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1427 | 1325 |
| LMArena Chinese | 1496 | 1372 |
| LMArena French | 1461 | 1374 |
| LMArena Korean | 1390 | 1304 |
| LMArena Russian | 1435 | 1338 |
| LMArena Spanish | 1448 | 1356 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1312 |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Trinity Large Thinking: 70.7 (#157)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1425 | 1334 |
Long Context Hy3 leads
Hy3: 44.1 (#70), Trinity Large Thinking: 41.2 (#139)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1443 | 1355 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Trinity Large Thinking: 54.0 (#152)
| Benchmark | Hy3 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1442 | 1340 |
| LMArena Creative Writing | 1399 | 1321 |
| LMArena Multi-Turn | 1436 | 1342 |
Frequently asked questions
Is Hy3 better than Trinity Large Thinking?
Hy3 is the stronger model overall, scoring 43.6 to 38.1 on the Noometry Index.
Which is cheaper, Hy3 or Trinity Large Thinking?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Hy3 or Trinity Large Thinking better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Trinity Large Thinking share?
17 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Trinity Large Thinking has 24.