Model comparison
C4ai Aya Expanse 32b vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 35.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
Cohere
Arcee AISummary
- They share 18 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 2 categories 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 54.0 to 42.4.
- Trinity Large Thinking accepts more context: 262K tokens versus 128K.
Side by side
| C4ai Aya Expanse 32b | Trinity Large Thinking | |
|---|---|---|
| Provider | Cohere | Arcee AI |
| Noometry Index | 35.3 | 38.1 |
| Released | 2024-10-24 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 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 Too close to call
C4ai Aya Expanse 32b: 34.3 (#227), Trinity Large Thinking: 33.8 (#238)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1197 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 22.3 (#183), Trinity Large Thinking: 16.3 (#298)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Trinity Large Thinking leads
C4ai Aya Expanse 32b: 31.4 (#195), Trinity Large Thinking: 34.9 (#149)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1200 | 1366 |
Knowledge Trinity Large Thinking leads
C4ai Aya Expanse 32b: 32.6 (#202), Trinity Large Thinking: 40.3 (#107)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 6.9% |
| LMArena Expert | 1182 | 1359 |
Multilingual Trinity Large Thinking leads
C4ai Aya Expanse 32b: 38.5 (#225), Trinity Large Thinking: 46.4 (#155)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1213 | 1325 |
| LMArena Chinese | 1210 | 1372 |
| LMArena French | 1247 | 1374 |
| LMArena German | 1199 | 1356 |
| LMArena Japanese | 1163 | 1312 |
| LMArena Korean | 1158 | 1304 |
| LMArena Russian | 1227 | 1338 |
| LMArena Spanish | 1193 | 1356 |
Instruction Following Trinity Large Thinking leads
C4ai Aya Expanse 32b: 62.9 (#232), Trinity Large Thinking: 70.7 (#157)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1196 | 1334 |
Long Context Trinity Large Thinking leads
C4ai Aya Expanse 32b: 37.2 (#215), Trinity Large Thinking: 41.2 (#139)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1228 | 1355 |
Writing & Preference Trinity Large Thinking leads
C4ai Aya Expanse 32b: 42.4 (#230), Trinity Large Thinking: 54.0 (#152)
| Benchmark | C4ai Aya Expanse 32b | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1224 | 1340 |
| LMArena Creative Writing | 1200 | 1321 |
| LMArena Multi-Turn | 1190 | 1342 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.1 to 35.3 on the Noometry Index.
Is C4ai Aya Expanse 32b or Trinity Large Thinking better for coding?
They score almost the same on coding (34.3 vs 33.8); test both on your own repository before choosing.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Trinity Large Thinking share?
18 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Trinity Large Thinking has 24.