Model comparison
Qwen-14B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 10 benchmarks with published results for both. Qwen-14B scores higher in 1 category and Trinity Large Thinking in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 53.8 to 27.6.
Side by side
| Qwen-14B | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 31.4 | 38.6 |
| Released | 2023-09-24 | 2026-04-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 80K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.80 |
| Results tracked | 18 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Qwen-14B: 31.2 (#288), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1071 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
Reasoning Qwen-14B leads
Qwen-14B: 19.6 (#257), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Trinity Large Thinking leads
Qwen-14B: 31.2 (#227), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1068 | 1366 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1360 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Trinity Large Thinking leads
Qwen-14B: 27.5 (#275), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1041 | 1325 |
| LMArena Chinese | 1077 | 1373 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1337 |
| LMArena Spanish | — | 1357 |
Instruction Following Trinity Large Thinking leads
Qwen-14B: 52.4 (#289), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1031 | 1334 |
Long Context Trinity Large Thinking leads
Qwen-14B: 31.3 (#280), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1028 | 1355 |
Writing & Preference Trinity Large Thinking leads
Qwen-14B: 27.6 (#299), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen-14B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1051 | 1340 |
| LMArena Creative Writing | 1028 | 1320 |
| LMArena Multi-Turn | 1022 | 1342 |
Frequently asked questions
Is Qwen-14B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 31.4 on the Noometry Index.
Is Qwen-14B or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 31.2 in the Noometry coding category.
How many benchmarks do Qwen-14B and Trinity Large Thinking share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Trinity Large Thinking has 24.