Model comparison
Granite 4.0 H Small vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 36.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
Arcee AISummary
- They share 14 benchmarks with published results for both. Granite 4.0 H Small scores higher in 2 categories and Trinity Large Thinking in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Trinity Large Thinking leads 53.8 to 43.8.
Side by side
| Granite 4.0 H Small | Trinity Large Thinking | |
|---|---|---|
| Provider | IBM | Arcee AI |
| Noometry Index | 36.5 | 38.6 |
| Released | — | 2026-04-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 80K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.80 |
| Results tracked | 19 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Granite 4.0 H Small: 36.4 (#209), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1249 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 24.4 (#163), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Trinity Large Thinking leads
Granite 4.0 H Small: 31.4 (#223), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1247 | 1366 |
| Omni-MATH | 29.6% | — |
Knowledge Trinity Large Thinking leads
Granite 4.0 H Small: 32.0 (#215), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 5.2% | 6.9% |
| LMArena Expert | 1251 | 1360 |
| MMLU-Pro | 56.9% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual Trinity Large Thinking leads
Granite 4.0 H Small: 38.6 (#228), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1216 | 1325 |
| LMArena Chinese | 1249 | 1373 |
| LMArena Russian | 1201 | 1337 |
| LMArena Spanish | 1258 | 1357 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
Instruction Following Trinity Large Thinking leads
Granite 4.0 H Small: 68.7 (#183), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1222 | 1334 |
| IFEval | 89% | — |
Long Context Trinity Large Thinking leads
Granite 4.0 H Small: 37.7 (#213), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1242 | 1355 |
Writing & Preference Trinity Large Thinking leads
Granite 4.0 H Small: 43.8 (#227), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Granite 4.0 H Small | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1241 | 1340 |
| LMArena Creative Writing | 1211 | 1320 |
| LMArena Multi-Turn | 1242 | 1342 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 36.5 on the Noometry Index.
Is Granite 4.0 H Small or Trinity Large Thinking better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 34.1 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Trinity Large Thinking share?
14 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Trinity Large Thinking has 24.