Model comparison
Qwen2.5-Coder-32B vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 33.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
Arcee AISummary
- They share 12 benchmarks with published results for both. Qwen2.5-Coder-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 writing & preference, where Trinity Large Thinking leads 53.8 to 41.6.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Trinity Large Thinking accepts more context: 262K tokens versus 33K.
Side by side
| Qwen2.5-Coder-32B | Trinity Large Thinking | |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 33.4 | 38.6 |
| Released | 2024-09-18 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 33K | 262K |
| Max output | 29K | 80K |
| Input $ / M tokens | $0.66 | $0.25 |
| Output $ / M tokens | $1 | $0.80 |
| Results tracked | 31 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Qwen2.5-Coder-32B: 22.6 (#333), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1276 | 1381 |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |
Reasoning Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 21.2 (#225), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 42.1% | — |
| LiveBench Data Analysis | 49.9% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 119.49 | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |
Math Trinity Large Thinking leads
Qwen2.5-Coder-32B: 33.3 (#204), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1251 | 1366 |
| LiveBench Math | 46.6% | — |
| GSM8K | 93% | — |
Knowledge Trinity Large Thinking leads
Qwen2.5-Coder-32B: 33.4 (#203), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1221 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |
Multilingual Trinity Large Thinking leads
Qwen2.5-Coder-32B: 37.8 (#235), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1205 | 1325 |
| LMArena Chinese | 1222 | 1373 |
| LMArena Russian | 1228 | 1337 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Spanish | — | 1357 |
Instruction Following Trinity Large Thinking leads
Qwen2.5-Coder-32B: 61.4 (#245), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1223 | 1334 |
| LiveBench Instruction Following | 58.7% | — |
Long Context Trinity Large Thinking leads
Qwen2.5-Coder-32B: 38.0 (#208), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1251 | 1355 |
Writing & Preference Trinity Large Thinking leads
Qwen2.5-Coder-32B: 41.6 (#240), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Qwen2.5-Coder-32B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1230 | 1340 |
| LMArena Creative Writing | 1174 | 1320 |
| LMArena Multi-Turn | 1222 | 1342 |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 33.4 on the Noometry Index.
Which is cheaper, Qwen2.5-Coder-32B 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; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is Qwen2.5-Coder-32B or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 33K.
How many benchmarks do Qwen2.5-Coder-32B and Trinity Large Thinking share?
12 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Trinity Large Thinking has 24.