Model comparison
Qwen1.5-32B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 17 benchmarks with published results for both. Qwen1.5-32B scores higher in 1 category and Trinity Large Thinking in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 13.5.
Side by side
| Qwen1.5-32B | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 30.5 | 38.6 |
| Released | 2024-02-04 | 2026-04-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 80K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.80 |
| Results tracked | 21 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Qwen1.5-32B: 31.7 (#282), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1155 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 32.3% | — |
| BigCodeBench Complete | 42% | — |
Reasoning Qwen1.5-32B leads
Qwen1.5-32B: 21.8 (#212), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1130 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Trinity Large Thinking leads
Qwen1.5-32B: 33.0 (#207), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1155 | 1366 |
Knowledge Trinity Large Thinking leads
Qwen1.5-32B: 13.5 (#296), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1126 | 1360 |
| GPQA Diamond | 30.7% | — |
| Vectara Hallucination Rate | — | 6.9% |
| MMLU | 74.4% | — |
Multilingual Trinity Large Thinking leads
Qwen1.5-32B: 31.4 (#259), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1106 | 1325 |
| LMArena Chinese | 1177 | 1373 |
| LMArena French | 1101 | 1374 |
| LMArena German | 1058 | 1356 |
| LMArena Japanese | 1027 | 1311 |
| LMArena Korean | 1008 | 1306 |
| LMArena Russian | 1073 | 1337 |
| LMArena Spanish | 1089 | 1357 |
Instruction Following Trinity Large Thinking leads
Qwen1.5-32B: 57.7 (#265), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1116 | 1334 |
Long Context Trinity Large Thinking leads
Qwen1.5-32B: 34.7 (#246), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1146 | 1355 |
Writing & Preference Trinity Large Thinking leads
Qwen1.5-32B: 34.2 (#271), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen1.5-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1137 | 1340 |
| LMArena Creative Writing | 1083 | 1320 |
| LMArena Multi-Turn | 1140 | 1342 |
Frequently asked questions
Is Qwen1.5-32B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 30.5 on the Noometry Index.
Is Qwen1.5-32B or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 31.7 in the Noometry coding category.
How many benchmarks do Qwen1.5-32B and Trinity Large Thinking share?
17 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Trinity Large Thinking has 24.